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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 27493
    Prev
    Next
    INDEX
    Explanations

    data lists

    np_max-act · gemini-2.0-flash

    mentions of counts or numeric quantities (tokens referring to numbers, amounts, or counts).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    —at
    -0.07
    /tree
    -0.07
    ocre
    -0.07
     &_
    -0.07
    (style
    -0.07
     brands
    -0.06
    нику
    -0.06
    多少
    -0.06
     bir
    -0.06
    Merge
    -0.06
    POSITIVE LOGITS
     Miguel
    0.07
    *</
    0.07
     ARGS
    0.06
    ."'";↵
    0.06
    ;

↵
    0.06
    спіль
    0.06
     GENERAL
    0.06
     FK
    0.06
    stackoverflow
    0.06
    ")
↵
    0.06
    Activations Density 0.057%

    No Known Activations