© 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. 3-RESID-POST-AA
    11. 93956
    Prev
    Next
    INDEX
    Explanations

    primary

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    開始
    -0.08
     favourites
    -0.07
    estimate
    -0.07
     droit
    -0.06
     favorites
    -0.06
     cookies
    -0.06
     resolve
    -0.06
    (scan
    -0.06
    Avoid
    -0.06
    _raw
    -0.06
    POSITIVE LOGITS
     leth
    0.07
     fus
    0.07
    イント
    0.06
     نمایش
    0.06
    หน
    0.06
     Roots
    0.06
     Naruto
    0.06
    ολ
    0.06
    .М
    0.06
    .Primary
    0.06
    Activations Density 0.005%

    No Known Activations