Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43639
    Prev
    Next
    INDEX
    Explanations

    bicycle gears/derailleurs

    np_max-act · gemini-2.0-flash

    specific bicycle components and their attributes.

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

    The neuron fires on mentions of specific bicycle hardware parts and model identifiers (e.g. brake calipers, screws, group-set names and numbers).

    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
    ού
    -0.07
    _CONTINUE
    -0.07
    ैप
    -0.06
    ین
    -0.06
     htmlFor
    -0.06
     technician
    -0.06
     Genetic
    -0.06
    年度
    -0.06
    .dll
    -0.06
     나가
    -0.06
    POSITIVE LOGITS
     أع
    0.06
    (big
    0.06
    setSize
    0.06
    _filtered
    0.06
     jih
    0.06
     Serena
    0.06
     Floating
    0.06
    getRow
    0.05
    -flag
    0.05
     diluted
    0.05
    Activations Density 0.016%

    No Known Activations