Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 5078
    Prev
    Next
    INDEX
    Explanations

    adjective

    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
     lanes
    -0.06
     pow
    -0.06
    igos
    -0.06
    н
    -0.06
     hubs
    -0.06
     pins
    -0.06
     eyes
    -0.06
    etections
    -0.06
     NG
    -0.06
    _rc
    -0.06
    POSITIVE LOGITS
     adjective
    0.13
    jectives
    0.09
    (station
    0.07
     dealership
    0.06
     passionately
    0.06
    /jpeg
    0.06
     maduras
    0.06
    *);↵↵
    0.06
    Chelsea
    0.06
     Aless
    0.06
    Activations Density 0.010%

    No Known Activations