© 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. 61130
    Prev
    Next
    INDEX
    Explanations

    chastity and control

    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
    legen
    -0.07
    _prov
    -0.07
    iče
    -0.07
     Jared
    -0.06
    rine
    -0.06
     abdomen
    -0.06
     Eaton
    -0.06
     uží
    -0.06
    alon
    -0.06
     Fury
    -0.06
    POSITIVE LOGITS
    ราช
    0.08
     Miscellaneous
    0.06
     дж
    0.06
    근
    0.06
    equipment
    0.06
     ;
↵
    0.06
     народу
    0.06
    684
    0.06
     worksheet
    0.06
     moto
    0.06
    Activations Density 0.017%

    No Known Activations