© 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. 74786
    Prev
    Next
    INDEX
    Explanations

    Numbers ending in "ty"

    np_max-act · gemini-2.0-flash

    The neuron detects spelled-out numerals (cardinal number words like “seventy,” “forty,” “eighty,” “thirty,” 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
     TAB
    -0.07
     varargin
    -0.07
    _aa
    -0.07
     เส
    -0.07
    498
    -0.07
     Ef
    -0.07
     obvious
    -0.07
     Daniels
    -0.07
     :],
    -0.06
    .getSystemService
    -0.06
    POSITIVE LOGITS
     twenty
    0.10
     ninety
    0.10
     thirty
    0.09
     seventy
    0.08
     eighty
    0.08
     Thirty
    0.07
     sixty
    0.07
     forty
    0.07
    ety
    0.07
     fifty
    0.07
    Activations Density 0.014%

    No Known Activations