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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 45401
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     bas
    -0.07
    _gradient
    -0.06
     eing
    -0.06
     slopes
    -0.06
    _half
    -0.06
    听
    -0.06
    次
    -0.06
    -prop
    -0.06
    location
    -0.06
    лагод
    -0.06
    POSITIVE LOGITS
     شاخه
    0.07
    NSURL
    0.06
    SupportedContent
    0.06
    (mt
    0.06
    $url
    0.06
    MAR
    0.06
     √
    0.06
     náp
    0.06
    枚
    0.06
    zeń
    0.06
    Activations Density 0.012%

    No Known Activations