© 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. 88972
    Prev
    Next
    INDEX
    Explanations

    Measurements of mass and weight

    np_max-act · gemini-2.0-flash

    conversations and logical questions regarding weights and measurements of materials.

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

    This neuron activates on terms and tokens related to weight or mass (e.g., “weight,” “weigh,” “mass,” “same” in weight comparisons).

    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
    álně
    -0.06
    .cls
    -0.06
    pkg
    -0.06
     ICommand
    -0.06
    cribing
    -0.06
    _mt
    -0.06
     lần
    -0.05
    promo
    -0.05
    кові
    -0.05
    msgs
    -0.05
    POSITIVE LOGITS
     βά
    0.08
    assuming
    0.07
    organizations
    0.07
     tt
    0.06
    QRSTUV
    0.06
    irmingham
    0.06
    THEN
    0.06
     television
    0.06
     nk
    0.06
     концентра
    0.06
    Activations Density 0.014%

    No Known Activations