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. 53714
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    -clean
    -0.07
    IDER
    -0.07
    /v
    -0.07
    ™
    -0.07
    []"
    -0.06
     Sand
    -0.06
     jim
    -0.06
    /sidebar
    -0.06
     builder
    -0.06
     wich
    -0.06
    POSITIVE LOGITS
     complexion
    0.07
     reluct
    0.06
     revoke
    0.06
    DBC
    0.06
     Signature
    0.06
    ための
    0.06
     flagged
    0.06
    (completion
    0.06
     dong
    0.06
    _channel
    0.06
    Activations Density 0.004%

    No Known Activations