© 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. 55431
    Prev
    Next
    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash

    words related to smartphone specifications and features.

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

    This neuron detects mentions of specific smartphone model names (especially Samsung Galaxy series identifiers).

    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
    Young
    -0.07
    Ar
    -0.06
    young
    -0.06
     Math
    -0.06
     thwart
    -0.06
     bul
    -0.06
     شر
    -0.06
    .When
    -0.06
     art
    -0.06
    Copyright
    -0.06
    POSITIVE LOGITS
    vocab
    0.07
    jualan
    0.06
    _↵↵
    0.06
     Lakers
    0.06
    )data
    0.06
     Playoff
    0.06
     مخصوص
    0.06
    inciple
    0.06
     PLL
    0.06
     routes
    0.06
    Activations Density 0.005%

    No Known Activations