© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128789
    Prev
    Next
    INDEX
    Explanations

    sun

    np_max-act · gemini-2.0-flash

    This neuron activates on words describing sunlight or the sun’s shining (e.g., sun, shining, casting, warm glow).

    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
     hire
    -0.07
     Fathers
    -0.07
    atform
    -0.06
     EXIT
    -0.06
     اقدام
    -0.06
     takový
    -0.06
    swers
    -0.06
    ійс
    -0.06
    ervlet
    -0.06
     řid
    -0.06
    POSITIVE LOGITS
     sun
    0.10
    sun
    0.08
     proclamation
    0.06
    	sn
    0.06
    warehouse
    0.06
     Olympics
    0.06
     cannon
    0.06
     Associations
    0.06
     Bomb
    0.06
     bomb
    0.06
    Activations Density 0.011%

    No Known Activations