© 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. 43534
    Prev
    Next
    INDEX
    Explanations

    cooking times

    np_max-act · gemini-2.0-flash

    The neuron activates on cooking and baking step words—particularly oven-related instructions (e.g. “Preheat,” “Bake”), time and temperature terms (“minutes,” “degrees”), and related action cues.

    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
    ことが
    -0.07
     Penguin
    -0.06
    cuda
    -0.06
     rain
    -0.06
     Paleo
    -0.06
     년도별
    -0.06
    除了
    -0.06
     jejichž
    -0.06
     DOI
    -0.06
     immediate
    -0.06
    POSITIVE LOGITS
    ></
    0.07
    RULE
    0.07
     groupe
    0.06
    ];
    ↵
    0.06
    <Long
    0.06
     gamb
    0.06
    ;"><?
    0.06
     وش
    0.06
    )
    
    ↵
    0.06
     Dive
    0.06
    Activations Density 0.012%

    No Known Activations