© 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
    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. 586
    Prev
    Next
    INDEX
    Explanations

    explosions

    np_max-act · gemini-2.0-flash

    This neuron activates on technical descriptions of a nuclear explosion (e.g., “nuclear,” “blast,” “explosion,” “shock wave,” “epicenter”) and finds passages detailing the effects or mechanics of a nuclear blast.

    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
    ?>↵
    -0.07
    fwrite
    -0.06
     Financial
    -0.06
                  ↵
    -0.06
    _tc
    -0.06
     Nuevo
    -0.06
     ----------------------------------------------------------------------------
    -0.06
    Sector
    -0.06
     Kaf
    -0.06
     Johann
    -0.06
    POSITIVE LOGITS
    appable
    0.07
    (upload
    0.07
    crets
    0.06
    ầy
    0.06
     overl
    0.06
     распростран
    0.06
    (rand
    0.06
    -checked
    0.06
    -plane
    0.06
     läng
    0.06
    Activations Density 0.027%

    No Known Activations