© 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. 15-RESID-POST-AA
    11. 90610
    Prev
    Next
    INDEX
    Explanations

    grammar and language

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    τερο
    -0.07
     Inherits
    -0.07
     首页第
    -0.07
     CircularProgress
    -0.07
    ?action
    -0.07
    _INLINE
    -0.06
    ..."↵↵
    -0.06
    itable
    -0.06
    _cipher
    -0.06
    HUD
    -0.06
    POSITIVE LOGITS
     Angela
    0.07
     V
    0.06
     twitter
    0.06
     counselling
    0.06
    _Register
    0.06
     Mi
    0.06
     Che
    0.06
     Lap
    0.06
     R
    0.06
     Media
    0.06
    Activations Density 0.028%

    No Known Activations