© 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. 39182
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and names

    np_max-act · gemini-2.0-flash

    This neuron activates on multi-letter uppercase sequences or acronyms (often in parentheses).

    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
    -employed
    -0.06
     polít
    -0.06
    знач
    -0.06
     merupakan
    -0.06
    scatter
    -0.06
     regional
    -0.06
     Attempts
    -0.06
     독일
    -0.06
    字符串
    -0.06
     регі
    -0.06
    POSITIVE LOGITS
     Ways
    0.06
     Computing
    0.06
     bucks
    0.06
     stiff
    0.06
    رج
    0.06
     JMP
    0.06
     Lac
    0.06
     BA
    0.06
    _DEF
    0.06
     rake
    0.06
    Activations Density 0.114%

    No Known Activations