© 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. 38596
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on instances of negation or exclusion words (e.g., “not,” “only,” “but”).

    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
     Approach
    -0.07
    .album
    -0.07
     softly
    -0.06
     confessed
    -0.06
    _TYPE
    -0.06
     степени
    -0.06
     pronunciation
    -0.06
     sammen
    -0.06
     Beled
    -0.06
     agreeing
    -0.06
    POSITIVE LOGITS
    inar
    0.07
    lesc
    0.07
    ',...↵
    0.07
     warp
    0.07
    APPING
    0.06
    eyle
    0.06
     azalt
    0.06
     kısa
    0.06
     +++
    0.06
    입
    0.06
    Activations Density 0.014%

    No Known Activations