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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 86776
    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
     Ward
    -0.07
    _CUR
    -0.06
    twenty
    -0.06
    卖
    -0.06
     although
    -0.06
    Ratio
    -0.06
     uno
    -0.06
    bour
    -0.06
    極
    -0.06
    167
    -0.06
    POSITIVE LOGITS
     performance
    0.07
    _CENTER
    0.07
    .arr
    0.06
    ={{↵
    0.06
    能
    0.06
    (Set
    0.06
     Report
    0.06
     motivate
    0.06
     responses
    0.06
    曾
    0.06
    Activations Density 0.080%

    No Known Activations