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

    Neuronpedia

    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. 128580
    Prev
    Next
    INDEX
    Explanations

    avoiding problems or prevention

    np_max-act · gemini-2.0-flash

    technical terms related to engineering or machinery, particularly in the context of sewing machines.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects words that describe preventing, reducing, or avoiding unwanted effects (e.g., “prevented,” “reducing,” “avoiding,” “suppression”).

    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
    артам
    -0.07
    rypton
    -0.07
    ||↵
    -0.06
     <+
    -0.06
     lofty
    -0.06
    _props
    -0.06
    elight
    -0.06
    جاد
    -0.06
    .elementAt
    -0.06
    ,M
    -0.06
    POSITIVE LOGITS
     conco
    0.07
     discriminatory
    0.07
    -themed
    0.07
     Quiet
    0.07
    ellation
    0.06
     Natasha
    0.06
    uggle
    0.06
     kaç
    0.06
    .experimental
    0.06
     COVER
    0.06
    Activations Density 0.114%

    No Known Activations