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. 11-RESID-POST-AA
    6. 101065
    Prev
    Next
    INDEX
    Explanations

    achieving a goal

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    附近
    -0.07
    connexion
    -0.07
    ML
    -0.07
    --------------
    -0.07
    *R
    -0.06
     Greenwich
    -0.06
    -owned
    -0.06
     obliv
    -0.06
     pride
    -0.06
     overridden
    -0.06
    POSITIVE LOGITS
    .roll
    0.06
    .waitKey
    0.06
     bande
    0.06
    ledge
    0.06
    izzazione
    0.06
    lag
    0.06
    Nach
    0.06
     promote
    0.06
    люб
    0.06
    oya
    0.05
    Activations Density 0.020%

    No Known Activations