© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 69409
    Prev
    Next
    INDEX
    Explanations

    Tub

    np_max-act · gemini-2.0-flash

    domain-specific topical keywords—often capitalized or appearing in titles and headings—that signal the subject of a passage.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sai
    -0.06
    max
    -0.06
    HAS
    -0.05
     resembles
    -0.05
     IMP
    -0.05
    효
    -0.05
    _shapes
    -0.05
     Mata
    -0.05
     is
    -0.05
    雙
    -0.05
    POSITIVE LOGITS
    öff
    0.07
    -port
    0.07
    ELCOME
    0.07
    GenerationStrategy
    0.07
                ↵↵
    0.06
     searchString
    0.06
     원
    0.06
     Angela
    0.06
    NEY
    0.06
    writeln
    0.06
    Activations Density 0.508%

    No Known Activations