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. 69038
    Prev
    Next
    INDEX
    Explanations

    istem

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that refer to “knowledge” and its study (epistemology) and related terms.

    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
     sulfate
    -0.08
     collisions
    -0.07
    ouncil
    -0.06
    /support
    -0.06
     sells
    -0.06
     маши
    -0.06
     nightclub
    -0.06
     Portable
    -0.06
    javascript
    -0.06
     ně
    -0.06
    POSITIVE LOGITS
     این
    0.08
    呆
    0.07
     Emblem
    0.07
    های
    0.06
     deriving
    0.06
     Tacoma
    0.06
     magical
    0.06
     起
    0.06
     exclusively
    0.06
    estination
    0.06
    Activations Density 0.005%

    No Known Activations