© 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. 30675
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any text patterns—it remains inactive and finds nothing.

    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
     Khan
    -0.07
    unnable
    -0.07
    unning
    -0.07
    Framework
    -0.07
     mó
    -0.07
    Narrated
    -0.06
    _unsigned
    -0.06
    .Op
    -0.06
    _NETWORK
    -0.06
    YPD
    -0.06
    POSITIVE LOGITS
    _TIMES
    0.06
     Trung
    0.06
     estados
    0.06
     Teh
    0.06
     Formatting
    0.06
    -threatening
    0.06
     campo
    0.06
    -अ
    0.06
     wholes
    0.06
     κο
    0.06
    Activations Density 0.008%

    No Known Activations