Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1432
    Prev
    Next
    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash

    The neuron fires on finance/trading jargon—especially terms naming financial instruments or strategies.

    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
    國
    -0.07
    Mos
    -0.07
    _expiry
    -0.07
     //////////////////////////////////////////////////////////////////////
    -0.07
    /
    ↵
    -0.06
    Alt
    -0.06
    ぬ
    -0.06
     shows
    -0.06
     >
    ↵
    -0.06
     similarly
    -0.06
    POSITIVE LOGITS
    @Data
    0.07
     самостоятельно
    0.07
    (Double
    0.06
    클
    0.06
    .spec
    0.06
     Spoj
    0.06
     Ball
    0.06
    <bits
    0.06
    .EventArgs
    0.06
     Whole
    0.06
    Activations Density 0.358%

    No Known Activations