© 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. 129917
    Prev
    Next
    INDEX
    Explanations

    of

    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
     extortion
    -0.06
    差
    -0.06
    _mode
    -0.06
     gimm
    -0.06
    ginas
    -0.06
    _category
    -0.06
    setVisibility
    -0.06
    319
    -0.06
     Střed
    -0.06
     має
    -0.06
    POSITIVE LOGITS
    sandbox
    0.07
    berger
    0.06
     scout
    0.06
    주의
    0.06
     （
    0.06
     scouting
    0.06
    #----------------------------------------------------------------------------
    0.06
     biochemical
    0.06
    VRTX
    0.06
    릉
    0.06
    Activations Density 0.008%

    No Known Activations