© 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
    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. 69196
    Prev
    Next
    INDEX
    Explanations

    else

    np_max-act · gemini-2.0-flash

    rules and mechanics related to gameplay in card games.

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

    The neuron never activates—it’s essentially “dead” and doesn’t detect any pattern.

    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
    使
    -0.07
    pos
    -0.06
     leng
    -0.06
     представ
    -0.06
    ensation
    -0.06
     detecting
    -0.06
     одной
    -0.06
    илися
    -0.06
    Score
    -0.06
    Sock
    -0.06
    POSITIVE LOGITS
    _SDK
    0.07
     conson
    0.07
     Conserv
    0.06
     constexpr
    0.06
    <Props
    0.06
    (tc
    0.06
     Pom
    0.06
    (iter
    0.06
     turnout
    0.06
     isim
    0.06
    Activations Density 0.022%

    No Known Activations