© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130139
    Prev
    Next
    INDEX
    Explanations

    Referring to figures

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on numeric tokens—especially decimals, measurements, figure numbers, and other numerical data.

    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
     insert
    -0.07
    compact
    -0.07
    _read
    -0.06
     BED
    -0.06
     antic
    -0.06
    Validity
    -0.06
     yapı
    -0.06
    Pg
    -0.06
     ftp
    -0.06
    CString
    -0.06
    POSITIVE LOGITS
    піон
    0.06
     сказала
    0.06
     Harden
    0.06
    }}],↵
    0.06
    руз
    0.06
     توجه
    0.06
     слишком
    0.06
     Bray
    0.06
     pochop
    0.06
    等
    0.06
    Activations Density 0.012%

    No Known Activations