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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 36403
    Prev
    Next
    INDEX
    Explanations

    sulfonates

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bees
    -0.06
    crow
    -0.06
     HEALTH
    -0.06
    +".
    -0.06
    Digit
    -0.06
    _prices
    -0.06
    	BOOST
    -0.05
    _SERVER
    -0.05
    Absent
    -0.05
    추
    -0.05
    POSITIVE LOGITS
    .listen
    0.08
     PED
    0.07
    .ol
    0.07
     infrared
    0.07
    (listener
    0.07
    PostalCodes
    0.07
    าห
    0.06
     obesity
    0.06
    Military
    0.06
    meg
    0.06
    Activations Density 0.004%

    No Known Activations