© 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. 41618
    Prev
    Next
    INDEX
    Explanations

    electrical circuits

    np_max-act · gemini-2.0-flash

    The neuron detects numeric values—especially floating‐point numbers or measurements—in the technical text.

    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
     opposes
    -0.08
    濃
    -0.07
    _ctrl
    -0.06
    _cleanup
    -0.06
     collo
    -0.06
    ept
    -0.06
     мона
    -0.06
     GFX
    -0.06
     matches
    -0.06
    ίο
    -0.06
    POSITIVE LOGITS
    prung
    0.06
     Đảng
    0.06
     Dropbox
    0.06
    си
    0.06
     Provided
    0.06
     シ
    0.06
    Nam
    0.06
    िकत
    0.06
     scarcely
    0.05
    ем
    0.05
    Activations Density 0.013%

    No Known Activations