© 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. 55853
    Prev
    Next
    INDEX
    Explanations

    NR

    np_max-act · gemini-2.0-flash

    The neuron fires on the adjective “high-level” (i.e. when text labels something as a high-level framework or tool).

    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
     заліз
    -0.07
    emotion
    -0.06
     isolation
    -0.06
     Support
    -0.06
     ambiance
    -0.06
    meldung
    -0.06
     fascism
    -0.06
     MOR
    -0.06
     focusing
    -0.06
    .CONTENT
    -0.06
    POSITIVE LOGITS
     bug
    0.07
     #[
    0.07
    ată
    0.06
    attached
    0.06
    localStorage
    0.06
     cân
    0.06
    )$_
    0.06
    \'
    0.06
    LEFT
    0.06
    +#
    0.06
    Activations Density 0.088%

    No Known Activations