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. 16170
    Prev
    Next
    INDEX
    Explanations

    telephone

    np_max-act · gemini-2.0-flash

    details regarding telecommunication systems and related technologies.

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

    The neuron fires on technical telephony infrastructure terms—especially references to digital subscriber lines (DSL), POTS, and related telephone‐line technologies.

    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
    elere
    -0.08
    322
    -0.07
     financ
    -0.07
     Symptoms
    -0.06
     isSuccess
    -0.06
     Alla
    -0.06
     miraculous
    -0.06
     Auditor
    -0.06
    coles
    -0.06
     onemoc
    -0.06
    POSITIVE LOGITS
     использов
    0.07
     svg
    0.07
    (iOS
    0.06
    جيل
    0.06
    _kses
    0.06
    センター
    0.06
     gboolean
    0.06
     ç
    0.06
    .raw
    0.06
    .Detail
    0.06
    Activations Density 0.012%

    No Known Activations