© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 35150
    Prev
    Next
    INDEX
    Explanations

    stop words

    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
    appear
    -0.07
    大き
    -0.07
    왔
    -0.06
    setw
    -0.06
    光
    -0.06
     Україна
    -0.06
     censorship
    -0.06
    _similarity
    -0.06
     名前
    -0.06
     か
    -0.06
    POSITIVE LOGITS
    .getObject
    0.07
    ="<?=
    0.06
    .DEBUG
    0.06
     NEO
    0.06
    挺
    0.06
    ौन
    0.06
     بودن
    0.06
    治
    0.06
     الج
    0.06
    .restore
    0.06
    Activations Density 0.614%

    No Known Activations