© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91632
    Prev
    Next
    INDEX
    Explanations

    deals, support, exchange

    np_max-act · gemini-2.0-flash

    historical events and their consequences.

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

    The neuron is essentially silent—it almost never activates and does not reliably detect any meaningful 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
     �
    -0.07
     Shot
    -0.06
     KB
    -0.06
    reasonable
    -0.06
     tür
    -0.06
    shot
    -0.06
    Initial
    -0.06
    好き
    -0.06
    eceği
    -0.06
    workflow
    -0.06
    POSITIVE LOGITS
     شاخه
    0.07
    compet
    0.06
     مرحله
    0.06
    내
    0.06
     Juni
    0.06
    igDecimal
    0.06
    variation
    0.06
     засід
    0.06
     markets
    0.06
    をか
    0.06
    Activations Density 0.075%

    No Known Activations