© 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. 6382
    Prev
    Next
    INDEX
    Explanations

    travel

    np_max-act · gemini-2.0-flash

    This neuron is primarily activated by mentions of sailing or sailboat excursions.

    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
    Voltage
    -0.06
    Bed
    -0.06
    summary
    -0.06
    dou
    -0.06
    #{@
    -0.06
    Bon
    -0.06
    .Decode
    -0.06
    ley
    -0.06
    会议
    -0.06
    drivers
    -0.06
    POSITIVE LOGITS
     soudu
    0.07
    apatkan
    0.07
     bilgileri
    0.07
     satın
    0.07
     frec
    0.07
     트
    0.06
     πρα
    0.06
    losure
    0.06
    elect
    0.06
     schw
    0.06
    Activations Density 0.019%

    No Known Activations