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. 23-RESID-POST-AA
    6. 104069
    Prev
    Next
    INDEX
    Explanations

    ki

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     strike
    -0.07
    -ar
    -0.06
     cannons
    -0.06
    .ContextCompat
    -0.06
    WAY
    -0.06
    Think
    -0.06
    Viewer
    -0.06
     meters
    -0.06
    neys
    -0.06
    ativa
    -0.06
    POSITIVE LOGITS
    pile
    0.07
    serious
    0.07
    香蕉
    0.06
     kombin
    0.06
     oppon
    0.06
    ?↵↵↵↵↵↵
    0.06
    tuğ
    0.06
    .blur
    0.06
     имму
    0.06
     gymn
    0.06
    Activations Density 0.005%

    No Known Activations