© 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. 89758
    Prev
    Next
    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals in code—e.g. any standalone numbers (with or without units) like “1px”, “100%”, “20px”, “2.60546875”, etc.

    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
     зменш
    -0.07
     revelations
    -0.06
    عة
    -0.06
    로나
    -0.06
     neighb
    -0.06
     همیشه
    -0.06
    Aliases
    -0.06
    Skip
    -0.06
     bidding
    -0.06
    SOFTWARE
    -0.06
    POSITIVE LOGITS
     itertools
    0.07
    期间
    0.07
    "He
    0.07
     emoji
    0.07
     laminate
    0.06
    ilebilir
    0.06
    ,“
    0.06
     مقاله
    0.06
    atel
    0.06
     Profession
    0.06
    Activations Density 0.008%

    No Known Activations