© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 731
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash

    This neuron detects legal procedural phrasing—specifically the recurring “petition for review”/“review of a decision or order” language in appellate‐style headings.

    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
     extrapol
    -0.08
     самого
    -0.08
    obs
    -0.07
    JoinColumn
    -0.07
     ecstasy
    -0.06
     emin
    -0.06
     грун
    -0.06
     проек
    -0.06
     �
    -0.06
    igi
    -0.06
    POSITIVE LOGITS
     concerning
    0.07
    _radio
    0.07
     Hồng
    0.06
     Blue
    0.06
    慌
    0.06
    leme
    0.06
     seasoned
    0.06
     suitable
    0.06
     môn
    0.06
     asthma
    0.06
    Activations Density 0.005%

    No Known Activations