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. 3-RESID-POST-AA
    6. 94736
    Prev
    Next
    INDEX
    Explanations

    S

    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
     Fair
    -0.07
    ovenant
    -0.06
     fair
    -0.06
     Covenant
    -0.06
    <Token
    -0.06
    'field
    -0.06
     shortcomings
    -0.06
     neighbourhood
    -0.06
    $value
    -0.06
     farms
    -0.06
    POSITIVE LOGITS
     Patrol
    0.09
    Accessible
    0.07
     искус
    0.07
    BS
    0.07
    pps
    0.07
    PS
    0.07
    S
    0.07
    .onreadystatechange
    0.06
    öt
    0.06
    なお
    0.06
    Activations Density 0.003%

    No Known Activations