© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 94115
    Prev
    Next
    INDEX
    Explanations

    back

    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
    叶
    -0.07
     GUI
    -0.07
     Dist
    -0.06
     Menu
    -0.06
     VIC
    -0.06
    委员会
    -0.06
     savory
    -0.06
    _warn
    -0.06
     VR
    -0.06
    .card
    -0.06
    POSITIVE LOGITS
     back
    0.14
     BACK
    0.08
     backs
    0.08
    -back
    0.08
    _back
    0.08
     Back
    0.07
     attack
    0.07
     기업
    0.07
    back
    0.06
     reak
    0.06
    Activations Density 0.020%

    No Known Activations