© 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
    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. 23153
    Prev
    Next
    INDEX
    Explanations

    code and fill-in-blanks

    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
    imei
    -0.07
     brazil
    -0.07
    .RegularExpressions
    -0.07
    ської
    -0.07
    .AutoScaleMode
    -0.07
    %d
    -0.07
    .dropout
    -0.07
    _property
    -0.06
    Controls
    -0.06
     ولكن
    -0.06
    POSITIVE LOGITS
    Memo
    0.06
    aken
    0.06
     memb
    0.06
     polym
    0.06
     Поч
    0.06
    brook
    0.06
    �
    0.06
    ngthen
    0.06
    umpy
    0.05
     irritated
    0.05
    Activations Density 0.049%

    No Known Activations