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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 109903
    Prev
    Next
    INDEX
    Explanations

    bodily

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “bodily,” i.e. references to bodily functions or the body’s physical processes.

    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
    (children
    -0.06
    ама
    -0.06
     součástí
    -0.06
     onItemClick
    -0.06
    acji
    -0.06
    unteer
    -0.06
    üven
    -0.06
    ference
    -0.06
     inference
    -0.06
     then
    -0.06
    POSITIVE LOGITS
     bodily
    0.10
     systemctl
    0.07
    igid
    0.07
    __(
    0.06
     relating
    0.06
     Presidential
    0.06
    学
    0.06
    olly
    0.06
    دن
    0.06
    Postal
    0.06
    Activations Density 0.006%

    No Known Activations