© 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. 43375
    Prev
    Next
    INDEX
    Explanations

    whisk

    np_max-act · gemini-2.0-flash

    The neuron fires on imperative cooking action verbs (like “whisk,” “stir,” “beat,” and similar mixing instructions).

    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
    (peer
    -0.07
    (payment
    -0.07
     Lua
    -0.06
    eos
    -0.06
    _DROP
    -0.06
    yaml
    -0.06
    spin
    -0.06
     capability
    -0.06
     نقد
    -0.06
    (MPI
    -0.06
    POSITIVE LOGITS
     )↵↵↵
    0.08
    _ht
    0.08
    -instagram
    0.07
     excluded
    0.07
     lecturer
    0.07
    “In
    0.07
    815
    0.06
     �
    0.06
    ]?
    0.06
    -readable
    0.06
    Activations Density 0.002%

    No Known Activations