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. 54660
    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
    وس
    -0.07
    _preview
    -0.06
     duyg
    -0.06
     समय
    -0.06
     zaw
    -0.06
    >You
    -0.06
    tribution
    -0.06
    كام
    -0.06
    Spacing
    -0.06
    凌
    -0.06
    POSITIVE LOGITS
     lien
    0.08
     rural
    0.07
    ép
    0.06
    NSNotificationCenter
    0.06
    uds
    0.06
    .Annotation
    0.06
    平台
    0.06
    emergency
    0.06
    ılmaz
    0.06
    /topic
    0.06
    Activations Density 0.000%

    No Known Activations