© 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. 30068
    Prev
    Next
    INDEX
    Explanations

    unidentified person

    np_max-act · gemini-2.0-flash

    The neuron fires on references to unspecified or unknown individuals (e.g. descriptions of people whose identity isn’t provided).

    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
    /__
    -0.07
    ICC
    -0.06
    -bed
    -0.06
    Budget
    -0.06
    -east
    -0.06
     recap
    -0.06
    QUERY
    -0.06
    BX
    -0.06
     kidd
    -0.06
    POSITIVE LOGITS
     francais
    0.07
    ầng
    0.06
     Outs
    0.06
     sem
    0.06
     müzik
    0.06
     بشكل
    0.06
    _fitness
    0.06
     Flor
    0.06
     ded
    0.06
     conducive
    0.06
    Activations Density 0.006%

    No Known Activations