© 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. 6760
    Prev
    Next
    INDEX
    Explanations

    basal

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric measurement tokens (decimal values).

    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
     그러
    -0.07
    _iteration
    -0.06
    .delete
    -0.06
    Purpose
    -0.06
    293
    -0.06
     simplement
    -0.06
    DRV
    -0.06
    电影
    -0.06
    请选择
    -0.06
    roup
    -0.06
    POSITIVE LOGITS
     dull
    0.08
     crushers
    0.06
    /,
    0.06
    .Provider
    0.06
     bureaucrats
    0.06
    ôt
    0.06
    uvo
    0.06
    aktiv
    0.06
     kä
    0.06
    getUrl
    0.06
    Activations Density 0.005%

    No Known Activations