© 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. 19-RESID-POST-AA
    11. 54182
    Prev
    Next
    INDEX
    Explanations

    possessive "'s"

    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
    Philadelphia
    -0.07
     čtyři
    -0.07
    ...');↵
    -0.06
    倉
    -0.06
    Doctrine
    -0.06
    iego
    -0.06
     Nhân
    -0.06
    	div
    -0.06
    ियर
    -0.06
    vou
    -0.06
    POSITIVE LOGITS
     spokes
    0.07
     fence
    0.07
     appropri
    0.07
     опас
    0.06
     ξ
    0.06
    _CANCEL
    0.06
     resize
    0.06
     subt
    0.06
     bosses
    0.06
    ilee
    0.06
    Activations Density 0.010%

    No Known Activations