© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68920
    Prev
    Next
    INDEX
    Explanations

    License

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of license‐related terms (e.g. “License,” “Public License,” “licenses,” etc.) in file headers or comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    fast
    -0.07
    司
    -0.07
    _questions
    -0.07
     VAR
    -0.06
    otp
    -0.06
    ason
    -0.06
    stre
    -0.06
    acak
    -0.06
    bold
    -0.06
     qualifiers
    -0.06
    POSITIVE LOGITS
    ,image
    0.07
    	conn
    0.06
     monot
    0.06
    ServerError
    0.06
    !');↵
    0.06
    -)
    0.06
    -tm
    0.06
    __)↵↵↵
    0.06
    ]=='
    0.06
    /";↵↵
    0.06
    Activations Density 0.013%

    No Known Activations