© 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. 7-RESID-POST-AA
    11. 9778
    Prev
    Next
    INDEX
    Explanations

    Rec

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     |
↵
    -0.07
     birth
    -0.06
     astro
    -0.06
    ＊
    -0.06
    ---↵
    -0.06
     yêu
    -0.06
    िप
    -0.06
     зан
    -0.06
    PURE
    -0.06
    _hit
    -0.06
    POSITIVE LOGITS
    "label
    0.06
     pitcher
    0.06
    ,list
    0.06
    ｗｗ
    0.06
    lor
    0.06
    fig
    0.06
    （平成
    0.06
     €
    0.06
    ..."↵↵
    0.06
     Erectile
    0.06
    Activations Density 0.274%

    No Known Activations