Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 93733
    Prev
    Next
    INDEX
    Explanations

    lation

    np_max-act · gemini-2.0-flash
    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
    _scripts
    -0.08
    ियम
    -0.07
    _EFFECT
    -0.07
     GAS
    -0.07
    AIN
    -0.07
     Π
    -0.07
    Spin
    -0.07
    ViewInit
    -0.06
     SOP
    -0.06
    swap
    -0.06
    POSITIVE LOGITS
    195
    0.07
     lắng
    0.06
     Aluminum
    0.06
     defendant
    0.06
     leo
    0.06
    طح
    0.06
     Dost
    0.06
    (datas
    0.06
     Eaton
    0.06
     undermine
    0.06
    Activations Density 0.013%

    No Known Activations