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. 83812
    Prev
    Next
    INDEX
    Explanations

    encourage

    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
     사이
    -0.07
     identities
    -0.06
     towing
    -0.06
     indent
    -0.06
     sovereignty
    -0.06
     apart
    -0.06
    员
    -0.06
     вла
    -0.06
    Projection
    -0.06
     bán
    -0.06
    POSITIVE LOGITS
     encourage
    0.10
     encourages
    0.09
     encouragement
    0.08
     encouraged
    0.08
     encouraging
    0.08
    Rib
    0.08
     discourage
    0.08
     cheering
    0.07
    cher
    0.07
     Guidance
    0.07
    Activations Density 0.011%

    No Known Activations