© 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. 89904
    Prev
    Next
    INDEX
    Explanations

    Emails and dialogues

    np_max-act · gemini-2.0-flash

    This neuron spotlights tokens in the doctor's (assistant’s) turns in the medical‐dialogue transcript.

    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
    _sem
    -0.07
     dụ
    -0.06
    é
    -0.06
    روم
    -0.06
    .MockMvc
    -0.06
    -Pack
    -0.06
     Orchestra
    -0.06
     Almighty
    -0.06
     Rai
    -0.06
     Rabbi
    -0.06
    POSITIVE LOGITS
    ็นว
    0.07
    물을
    0.06
    _include
    0.06
     aunque
    0.06
     absorbed
    0.06
    Then
    0.06
     nouvelles
    0.06
    .problem
    0.06
     colony
    0.06
    (env
    0.06
    Activations Density 0.032%

    No Known Activations