Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 127776
    Prev
    Next
    INDEX
    Explanations

    Enron emails

    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
    anced
    -0.08
     QUESTION
    -0.08
    oken
    -0.06
    Chars
    -0.06
    ancing
    -0.06
     quá
    -0.06
    .nextDouble
    -0.06
     shortages
    -0.06
    _fill
    -0.06
    629
    -0.06
    POSITIVE LOGITS
    (Spring
    0.07
     Kontakt
    0.06
     د
    0.06
     learned
    0.06
    .csrf
    0.06
    duk
    0.06
     ActionType
    0.06
     useSelector
    0.06
     useEffect
    0.06
     EntityState
    0.06
    Activations Density 0.021%

    No Known Activations