© 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. 35227
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     corrective
    -0.06
    320
    -0.06
     contrasting
    -0.06
     mundo
    -0.06
     karış
    -0.06
     prosecution
    -0.06
     Serialize
    -0.06
     fodder
    -0.06
     straightforward
    -0.06
     Restricted
    -0.06
    POSITIVE LOGITS
    observations
    0.07
     виступ
    0.07
     veil
    0.06
    ディース
    0.06
    ासन
    0.06
    ouch
    0.06
    apters
    0.06
     엘
    0.06
    ейчас
    0.06
    шая
    0.06
    Activations Density 0.016%

    No Known Activations