© 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. 128758
    Prev
    Next
    INDEX
    Explanations

    D

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point number tokens (i.e. the decimal probability 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
    監督
    -0.07
     warmer
    -0.07
    /navigation
    -0.06
    美國
    -0.06
     volte
    -0.06
     assistir
    -0.06
    urlpatterns
    -0.06
    March
    -0.06
     lotion
    -0.06
    Acceler
    -0.06
    POSITIVE LOGITS
     D
    0.07
    (any
    0.07
     D
    0.07
     madness
    0.07
     Detail
    0.07
    [dim
    0.07
    IOD
    0.07
     idi
    0.07
     outliers
    0.07
    4
    0.07
    Activations Density 0.010%

    No Known Activations