© 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. 6488
    Prev
    Next
    INDEX
    Explanations

    hang

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of items being hung or suspended (e.g., “hung,” “hanging”).

    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
     projectName
    -0.07
     Tours
    -0.06
     milion
    -0.06
     trhu
    -0.06
     cheg
    -0.06
     Doğum
    -0.06
     Evelyn
    -0.06
    LoadIdentity
    -0.06
    'ye
    -0.06
    -ch
    -0.06
    POSITIVE LOGITS
    olumn
    0.07
    도
    0.07
     bụi
    0.07
     اگر
    0.06
     IconButton
    0.06
     hanging
    0.06
    Hooks
    0.06
     hinge
    0.06
    089
    0.06
    _database
    0.06
    Activations Density 0.020%

    No Known Activations