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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 35879
    Prev
    Next
    INDEX
    Explanations

    <

    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
    (te
    -0.07
     positive
    -0.06
    ention
    -0.06
    (lr
    -0.06
     sequences
    -0.06
    >{@
    -0.06
    }:
    -0.06
     เท
    -0.06
    (bin
    -0.06
    amate
    -0.06
    POSITIVE LOGITS
     gid
    0.07
     Bruno
    0.07
     reply
    0.07
    KT
    0.07
     Differential
    0.07
     atIndex
    0.07
     stabilized
    0.07
     Odds
    0.06
    OUTPUT
    0.06
     SALE
    0.06
    Activations Density 0.004%

    No Known Activations