© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38773
    Prev
    Next
    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash

    This neuron detects decimal numeric values (floating‐point numbers) in the text.

    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
     včetně
    -0.07
    conv
    -0.06
     sagt
    -0.06
    "]↵
    -0.06
     rencontr
    -0.06
     cartel
    -0.06
    거리
    -0.06
     Scheme
    -0.06
    ичні
    -0.06
    ungeons
    -0.06
    POSITIVE LOGITS
     Denn
    0.07
     perverse
    0.07
    _dropdown
    0.07
     liv
    0.06
     Ver
    0.06
     Üy
    0.06
    _IF
    0.06
    inverse
    0.06
    (INFO
    0.06
     Gre
    0.06
    Activations Density 0.010%

    No Known Activations