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. 83401
    Prev
    Next
    INDEX
    Explanations

    retain

    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
    -mod
    -0.07
    Pos
    -0.07
     �
    -0.06
     kiện
    -0.06
     데이터
    -0.06
    cpt
    -0.06
     động
    -0.06
     tv
    -0.06
    опри
    -0.06
    Vertices
    -0.06
    POSITIVE LOGITS
     exploiting
    0.07
    .refs
    0.07
    OO
    0.07
    -panel
    0.06
    ->[
    0.06
     }↵
    0.06
    apons
    0.06
    oner
    0.06
     honorary
    0.06
     })(
    0.06
    Activations Density 0.000%

    No Known Activations