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. 15-RESID-POST-AA
    6. 12497
    Prev
    Next
    INDEX
    Explanations

    Dependencies

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    规划
    -0.07
    Born
    -0.06
    ver
    -0.06
    .Member
    -0.06
    кур
    -0.06
    (read
    -0.06
    Surv
    -0.06
     Freddie
    -0.06
    umi
    -0.06
    кі
    -0.06
    POSITIVE LOGITS
    (blog
    0.07
     hostel
    0.07
    (gray
    0.07
    }↵↵↵↵↵
    0.06
    /groups
    0.06
     migraine
    0.06
     bots
    0.06
     Previous
    0.06
    ?"↵↵
    0.06
    '''↵↵
    0.06
    Activations Density 0.001%

    No Known Activations