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. 11373
    Prev
    Next
    INDEX
    Explanations

    is are

    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
    ston
    -0.06
    JD
    -0.06
     paramount
    -0.05
    %m
    -0.05
     blob
    -0.05
     methodology
    -0.05
     df
    -0.05
    _controls
    -0.05
    _TIMEOUT
    -0.05
     olmam
    -0.05
    POSITIVE LOGITS
     résult
    0.09
    );\
    0.07
     Filter
    0.07
    ίκη
    0.07
     filter
    0.07
    .world
    0.07
    /thumb
    0.07
    /fire
    0.07
    ูกค
    0.07
    .delete
    0.06
    Activations Density 0.143%

    No Known Activations