© 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. 91962
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    expressions of emotional distress and challenges with mental well-being.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on imperative action verbs used to give suggestions or instructions (e.g., “identify,” “find,” “practice,” “hold,” etc.).

    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
    terior
    -0.06
     इसक
    -0.06
    Deleted
    -0.06
    도록
    -0.06
     된
    -0.06
    )").
    -0.06
     해야
    -0.06
    	Simple
    -0.06
    関
    -0.06
    薄
    -0.06
    POSITIVE LOGITS
     구
    0.07
    .Sum
    0.07
    ardım
    0.06
    match
    0.06
     createTime
    0.06
    ke
    0.06
     FirebaseDatabase
    0.06
     الوز
    0.06
    .mode
    0.06
     δι
    0.06
    Activations Density 0.041%

    No Known Activations