© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 106767
    Prev
    Next
    INDEX
    Explanations

    second

    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
     olacaktır
    -0.07
     исход
    -0.06
    院
    -0.06
     meslek
    -0.06
     █████
    -0.06
     UIBar
    -0.06
    strstr
    -0.06
     seront
    -0.06
     withheld
    -0.06
    997
    -0.05
    POSITIVE LOGITS
    .pojo
    0.09
    gradation
    0.08
    ypass
    0.07
    mons
    0.07
    submitButton
    0.07
    aversable
    0.07
     collisions
    0.07
    .ToDateTime
    0.07
    çois
    0.06
     approaches
    0.06
    Activations Density 0.034%

    No Known Activations