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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6088
    Prev
    Next
    INDEX
    Explanations

    brackets and parenthesis

    np_max-act · gemini-2.0-flash

    code snippets related to mathematical series and functions in programming languages.

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

    This neuron detects references to foreign‐function interface operations (ffi), especially allocation or dereferencing of foreign pointers.

    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
    bairro
    -0.07
    ()}↵
    -0.07
     harbour
    -0.07
    .restart
    -0.06
     southwestern
    -0.06
     plaza
    -0.06
     tm
    -0.06
     nakne
    -0.06
    太
    -0.06
     stars
    -0.06
    POSITIVE LOGITS
    ^{-
    0.08
     Oxygen
    0.07
    -generator
    0.07
    ovable
    0.06
     Debug
    0.06
     slipping
    0.06
     kancel
    0.06
     baking
    0.06
     Align
    0.06
     imprisonment
    0.06
    Activations Density 0.009%

    No Known Activations