© 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. 15-RESID-POST-AA
    11. 111893
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OT
    -0.07
     zonder
    -0.07
    ourses
    -0.06
     кафед
    -0.06
    .manual
    -0.06
     flashy
    -0.06
     Temporary
    -0.06
    	element
    -0.06
    -mediated
    -0.06
     NSDictionary
    -0.06
    POSITIVE LOGITS
    >${
    0.07
    >S
    0.06
    <|eot_id|>
    0.06
    /E
    0.06
     Barb
    0.06
    
    0.06
    ©
    0.06
    
    0.06
    _Utils
    0.06
     ISR
    0.06
    Activations Density 0.146%

    No Known Activations