© 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. 57671
    Prev
    Next
    INDEX
    Explanations

    len

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: this neuron detects uses of the socket‐length parameter type (socklen_t) and related size arguments in socket API calls.

    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
    podob
    -0.07
    Wood
    -0.07
    ,but
    -0.06
    =log
    -0.06
     divisions
    -0.06
    &a
    -0.06
    ,',
    -0.06
     KING
    -0.06
    ,model
    -0.06
     amateurs
    -0.06
    POSITIVE LOGITS
    -db
    0.07
     Regards
    0.07
     Identified
    0.06
     adorable
    0.06
    <char
    0.06
     Olsen
    0.06
    -framework
    0.06
    roles
    0.06
    pike
    0.06
    .qq
    0.06
    Activations Density 0.001%

    No Known Activations