© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 52372
    Prev
    Next
    INDEX
    Explanations

    expressing surprise/disbelief

    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_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
     pure
    -0.06
    imed
    -0.06
    ицин
    -0.06
    Born
    -0.06
     Lambert
    -0.06
    ,tp
    -0.06
     mất
    -0.06
    drv
    -0.06
    委员
    -0.06
     Dor
    -0.06
    POSITIVE LOGITS
    Wait
    0.07
     엔
    0.07
     conglomer
    0.07
     Wait
    0.07
    belie
    0.07
    -Speed
    0.07
     prend
    0.07
    -media
    0.06
     sensor
    0.06
    .cal
    0.06
    Activations Density 0.005%

    No Known Activations