© 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. 58419
    Prev
    Next
    INDEX
    Explanations

    Quotation marks, parentheses

    np_max-act · gemini-2.0-flash

    terms related to software package licensing and compliance.

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

    The neuron activates on tokens involved in error‐handling or exception‐throwing constructs (e.g. calls to NewErrorWithError, HPX_THROW_EXCEPTION, etc.).

    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
     sah
    -0.07
     tic
    -0.06
    Merge
    -0.06
     Xi
    -0.06
     ου
    -0.06
    	gr
    -0.06
     �
    -0.06
     éxito
    -0.06
    ふ
    -0.06
    -blog
    -0.06
    POSITIVE LOGITS
    光
    0.08
     وقد
    0.07
    اعد
    0.07
     segments
    0.07
     classes
    0.06
    قة
    0.06
     얼마
    0.06
    không
    0.06
    []}
    0.06
    oplast
    0.06
    Activations Density 0.001%

    No Known Activations