© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58190
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    code snippets related to object instantiation and manipulation in programming languages.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects programming-action keywords—imperative or procedural terms like “for,” “create,” “using,” “select,” etc.—that typically introduce code operations or tasks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    過
    -0.07
     Continent
    -0.07
     periodically
    -0.07
    swana
    -0.06
     posicion
    -0.06
     shoulder
    -0.06
    μαι
    -0.06
     Proposal
    -0.06
     Tubes
    -0.06
     sự
    -0.06
    POSITIVE LOGITS
     nargin
    0.07
    те
    0.07
    _UNKNOWN
    0.06
    .md
    0.06
    moz
    0.06
     číslo
    0.06
     zbyt
    0.06
    .IO
    0.06
     truly
    0.06
    на
    0.06
    Activations Density 0.118%

    No Known Activations