© 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. 23-RESID-POST-AA
    6. 7638
    Prev
    Next
    INDEX
    Explanations

    sale

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rats
    -0.06
    RoleId
    -0.06
     капіт
    -0.06
    question
    -0.06
    axed
    -0.06
    *'
    -0.06
     موسیقی
    -0.06
    SR
    -0.06
    	screen
    -0.06
     theres
    -0.06
    POSITIVE LOGITS
    .visualization
    0.08
     geil
    0.08
     Peru
    0.07
    _CUSTOM
    0.06
    �
    0.06
    巨
    0.06
    ReadStream
    0.06
     каче
    0.06
    �
    0.06
     زنی
    0.06
    Activations Density 0.023%

    No Known Activations