© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 73385
    Prev
    Next
    INDEX
    Explanations

    Text excerpts

    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
     대해서
    -0.07
     sł
    -0.06
    itating
    -0.06
    PageRoute
    -0.06
     vous
    -0.06
    เปล
    -0.06
     phần
    -0.06
     estimator
    -0.06
     فشار
    -0.06
     rời
    -0.06
    POSITIVE LOGITS
    -windows
    0.07
     تجاری
    0.07
     Surround
    0.07
     Chicago
    0.06
     Plug
    0.06
     course
    0.06
     setShow
    0.06
     webView
    0.06
    %^
    0.06
    .union
    0.06
    Activations Density 0.000%

    No Known Activations