© 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
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 123232
    Prev
    Next
    INDEX
    Explanations

    finding

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    軽
    -0.06
    -indent
    -0.06
    banks
    -0.06
     PW
    -0.06
     лист
    -0.06
    _AST
    -0.06
    custom
    -0.06
     sacred
    -0.06
    ´s
    -0.06
     Kath
    -0.06
    POSITIVE LOGITS
    refund
    0.07
     crochet
    0.07
     <!--
    0.06
        ↵    ↵    ↵
    0.06
    acteria
    0.06
    /install
    0.06
    ."<
    0.06
    ']]);↵
    0.06
     технолог
    0.06
    xde
    0.06
    Activations Density 0.006%

    No Known Activations