© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43419
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to numeral tokens, especially those appearing as years, volume/page numbers, or other numeric reference details in bibliographic citations.

    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
    зации
    -0.06
     zoning
    -0.06
     honor
    -0.06
     normally
    -0.06
    Correction
    -0.06
     Normally
    -0.06
    's
    -0.06
    _Part
    -0.05
     judicial
    -0.05
    พาะ
    -0.05
    POSITIVE LOGITS
     velký
    0.07
    <"
    0.06
     Wouldn
    0.06
     beide
    0.06
    ön
    0.06
     برگزار
    0.06
    etiyle
    0.06
     elk
    0.06
     Byron
    0.06
    qn
    0.06
    Activations Density 0.009%

    No Known Activations