© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 45612
    Prev
    Next
    INDEX
    Explanations

    elle

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    weekday
    -0.07
    ulong
    -0.07
    Videos
    -0.07
    했습니다
    -0.07
    WE
    -0.06
     gönder
    -0.06
     societal
    -0.06
     счита
    -0.06
     tasty
    -0.06
     doub
    -0.06
    POSITIVE LOGITS
    acons
    0.06
    icorn
    0.06
     />)↵
    0.06
    ahaha
    0.06
     ask
    0.06
     فس
    0.06
    افع
    0.06
    템
    0.06
     initials
    0.06
    .DropDownStyle
    0.06
    Activations Density 0.000%

    No Known Activations