© 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. 19-RESID-POST-AA
    11. 31806
    Prev
    Next
    INDEX
    Explanations

    Spilling drinks

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lives
    -0.07
     ris
    -0.06
    uela
    -0.06
     decor
    -0.06
     absent
    -0.06
    ore
    -0.06
    ill
    -0.06
     festive
    -0.06
    does
    -0.06
    $db
    -0.06
    POSITIVE LOGITS
    。
↵
    0.07
     WHETHER
    0.07
    ptrdiff
    0.06
     џ
    0.06
    .TextAlignment
    0.06
    .Infof
    0.06
     NSObject
    0.06
    (expr
    0.06
    CardBody
    0.06
     tpl
    0.06
    Activations Density 0.021%

    No Known Activations