© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92160
    Prev
    Next
    INDEX
    Explanations

    R

    np_max-act · gemini-2.0-flash

    specific mentions of names in entertainment and music contexts.

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

    This neuron activates on capitalized name tokens—that is, individual words in proper names (especially personal names).

    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
     Knoxville
    -0.07
     formulated
    -0.07
    EMA
    -0.07
    .just
    -0.06
     SW
    -0.06
     zwar
    -0.06
     California
    -0.06
    -REAL
    -0.06
    enia
    -0.06
     потом
    -0.06
    POSITIVE LOGITS
    _ai
    0.07
     #$
    0.07
     Accepted
    0.06
     sketches
    0.06
    =localhost
    0.06
     NavLink
    0.06
     stap
    0.06
     fixture
    0.06
    包含
    0.06
    ้าอ
    0.06
    Activations Density 0.076%

    No Known Activations