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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 40599
    Prev
    Next
    INDEX
    Explanations

    science and medicine

    np_max-act · gemini-2.0-flash

    terms related to optical telecommunications and signal processing.

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

    The neuron selectively detects technical scientific terminology—especially specialized nouns naming measured properties, materials, or domain‐specific devices.

    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
    etak
    -0.06
     awful
    -0.06
    -books
    -0.06
    getColor
    -0.06
    ml
    -0.06
    nut
    -0.06
    694
    -0.06
    対
    -0.06
     mir
    -0.06
     نو
    -0.05
    POSITIVE LOGITS
    -react
    0.07
     أمريكي
    0.07
     [@
    0.06
    érie
    0.06
     сказ
    0.06
    gtk
    0.06
     peníze
    0.06
     involve
    0.06
    _FORCE
    0.06
    śli
    0.06
    Activations Density 0.394%

    No Known Activations