© 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. 109212
    Prev
    Next
    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash

    This neuron consistently activates on running explanatory answer text (the assistant’s response prose) rather than on user queries or metadata.

    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
    voor
    -0.08
    Checkpoint
    -0.07
    े�
    -0.07
     emiss
    -0.06
    avar
    -0.06
     velvet
    -0.06
    िथ
    -0.06
    арт
    -0.06
     hitch
    -0.06
    ifferences
    -0.06
    POSITIVE LOGITS
     Dies
    0.06
    "=>
    0.06
    IMPLIED
    0.06
     ｌ
    0.06
    262
    0.06
     startY
    0.06
     Coil
    0.06
     大阪
    0.06
     Isis
    0.06
    '%(
    0.06
    Activations Density 0.116%

    No Known Activations