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. 123216
    Prev
    Next
    INDEX
    Explanations

    1

    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
     RoundedRectangle
    -0.07
     priest
    -0.07
     کرد
    -0.07
    .registration
    -0.06
     улуч
    -0.06
     آیا
    -0.06
     çöz
    -0.06
     onActivityResult
    -0.06
     attic
    -0.06
    困
    -0.06
    POSITIVE LOGITS
    _pin
    0.06
    arnings
    0.06
    دیگر
    0.06
     antlr
    0.06
    صح
    0.06
    _cliente
    0.06
    igh
    0.06
    ylv
    0.06
     wrongly
    0.06
    ORIES
    0.06
    Activations Density 0.003%

    No Known Activations