Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 42120
    Prev
    Next
    INDEX
    Explanations

    cooking stove

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of cooking heat sources or equipment (e.g., “stove,” “heat,” “fire”).

    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
     tweeted
    -0.07
    .classes
    -0.06
    _FAST
    -0.06
     Newspaper
    -0.06
    ContainerGap
    -0.06
    引用
    -0.06
     paralysis
    -0.06
     馬
    -0.06
    outil
    -0.06
     PASS
    -0.06
    POSITIVE LOGITS
    Pieces
    0.06
    ufe
    0.06
     broadcasts
    0.06
    .ImageIcon
    0.06
    venta
    0.06
     sopr
    0.06
     ver
    0.06
     candidates
    0.06
    епти
    0.06
    vern
    0.06
    Activations Density 0.007%

    No Known Activations