Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 36662
    Prev
    Next
    INDEX
    Explanations

    PHP code and errors

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    čně
    -0.06
    buf
    -0.06
     lx
    -0.06
    보험
    -0.06
     Qatar
    -0.06
    、
    -0.06
    Elapsed
    -0.06
     exploding
    -0.06
    Unmount
    -0.06
    Neighbors
    -0.06
    POSITIVE LOGITS
    _REMOVE
    0.08
     publik
    0.07
     classes
    0.07
     jsx
    0.07
    Poster
    0.06
     sidew
    0.06
    .DEFAULT
    0.06
     modify
    0.06
     semantic
    0.06
     appe
    0.06
    Activations Density 0.010%

    No Known Activations