© 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. 91646
    Prev
    Next
    INDEX
    Explanations

    credit

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the word “credit” (especially in “credit card” and related financial contexts).

    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
     JA
    -0.09
     Hanson
    -0.08
     jPanel
    -0.07
     Newman
    -0.07
    森
    -0.07
     JPanel
    -0.07
    _sess
    -0.07
    iomanip
    -0.07
    ops
    -0.07
    _none
    -0.07
    POSITIVE LOGITS
     credit
    0.15
     Credit
    0.13
     credits
    0.11
    Credit
    0.11
    credit
    0.10
    credits
    0.09
     Credits
    0.09
    Credits
    0.08
     credited
    0.08
    credible
    0.07
    Activations Density 0.013%

    No Known Activations