© 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. 41673
    Prev
    Next
    INDEX
    Explanations

    Suffixes (especially "ine")

    np_max-act · gemini-2.0-flash

    The neuron primarily detects numeric measurement values—floating‐point numbers—typical of quantitative data in scientific reporting.

    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
    _dist
    -0.07
     일어
    -0.06
     соответствии
    -0.06
     згідно
    -0.06
     ölçü
    -0.06
     fold
    -0.06
     derail
    -0.06
     preparations
    -0.06
     Clark
    -0.06
     Sel
    -0.05
    POSITIVE LOGITS
    @Path
    0.08
     nam
    0.07
     HS
    0.07
     Entries
    0.07
    ávě
    0.07
     pueda
    0.07
    _LICENSE
    0.07
    :///
    0.07
    .uc
    0.06
     nej
    0.06
    Activations Density 0.013%

    No Known Activations