© 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. 7-RESID-POST-AA
    11. 97389
    Prev
    Next
    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash

    expressions that signal contrast or negation, marking exceptions or reversals of a prior statement.

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    自然
    -0.07
    _life
    -0.07
     Rift
    -0.07
    메
    -0.06
    す
    -0.06
     デ
    -0.06
    SessionFactory
    -0.06
     NHL
    -0.06
    121
    -0.06
    ону
    -0.06
    POSITIVE LOGITS
    );
↵
↵
    0.07
    Từ
    0.07
     Barang
    0.06
     Splash
    0.06
     anxious
    0.06
     Figures
    0.06
     stabbing
    0.06
    );
↵
    0.06
     Voyage
    0.06
    :↵↵
    0.06
    Activations Density 0.143%

    No Known Activations