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. 19-RESID-POST-AA
    6. 127478
    Prev
    Next
    INDEX
    Explanations

    Quotation marks, angle brackets

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    051
    -0.07
    Nearly
    -0.06
    18
    -0.06
    \Models
    -0.06
     Fiber
    -0.06
    -spacing
    -0.06
    registers
    -0.06
    creasing
    -0.06
     Stevens
    -0.06
    pred
    -0.06
    POSITIVE LOGITS
    a
    0.09
    k
    0.08
                
    ↵
    0.08
    '
    0.08
    >}
    0.07
     klar
    0.07
    “
    0.07
    al
    0.07
    _kategori
    0.07
     ")↵↵
    0.07
    Activations Density 0.108%

    No Known Activations