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. 108530
    Prev
    Next
    INDEX
    Explanations

    I

    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
    -leg
    -0.06
    ontrol
    -0.06
    .rep
    -0.06
    ITLE
    -0.06
    걸
    -0.06
    [o
    -0.06
    inde
    -0.06
     tiener
    -0.06
    Mutable
    -0.06
    ू
    -0.06
    POSITIVE LOGITS
    :UIControlStateNormal
    0.07
     early
    0.07
    getName
    0.06
     Benjamin
    0.06
     Spanish
    0.06
    )!↵
    0.06
     السلام
    0.06
    E
    0.06
    .colorbar
    0.06
    不断
    0.06
    Activations Density 0.000%

    No Known Activations