© 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. 126642
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on document‐style headings and metadata labels (e.g. section titles, field names, or other header text).

    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
     releases
    -0.07
     decides
    -0.06
     数
    -0.06
     gọn
    -0.06
     leads
    -0.06
    ('$
    -0.06
     terms
    -0.06
     importantes
    -0.06
     basic
    -0.06
     변수
    -0.06
    POSITIVE LOGITS
     première
    0.07
    olean
    0.07
    دن
    0.07
     Utt
    0.07
     일본
    0.06
     relativ
    0.06
     próximo
    0.06
    .setLayout
    0.06
     cinsel
    0.06
     janvier
    0.06
    Activations Density 0.083%

    No Known Activations