© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44340
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens representing decimal scores (floating-point numbers), such as confidence or 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
    讨
    -0.07
     zaměř
    -0.06
    905
    -0.06
     Conrad
    -0.06
    (errno
    -0.06
    .metamodel
    -0.06
    espoň
    -0.06
     culinary
    -0.06
     corrosion
    -0.06
    paint
    -0.06
    POSITIVE LOGITS
     cac
    0.06
     der
    0.06
    (action
    0.06
    fono
    0.06
     fontWithName
    0.06
     Fact
    0.06
    _lastname
    0.06
    υτό
    0.06
    ifestyles
    0.06
     Capitals
    0.06
    Activations Density 0.034%

    No Known Activations