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. 83404
    Prev
    Next
    INDEX
    Explanations

    doors and gates opening

    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
     jurors
    -0.06
    .Word
    -0.06
    терес
    -0.06
    ůležit
    -0.06
    orption
    -0.06
    бав
    -0.06
     clicked
    -0.06
    493
    -0.05
     STORE
    -0.05
     έναν
    -0.05
    POSITIVE LOGITS
     Expr
    0.07
    奴
    0.06
     उस
    0.06
    až
    0.06
     activist
    0.06
     quam
    0.06
     callable
    0.06
    roi
    0.06
     srdce
    0.06
     เขต
    0.06
    Activations Density 0.032%

    No Known Activations