© 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. 73550
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    np_max-act · gemini-2.0-flash

    responses related to AI capabilities and consciousness.

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

    This neuron detects mentions of the AI model itself (tokens like “AI” and “model”) in the text.

    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
    properties
    -0.06
    оров
    -0.06
    processors
    -0.06
    čit
    -0.06
    -service
    -0.06
     coatings
    -0.06
    ease
    -0.06
    chemistry
    -0.06
    outine
    -0.06
    ARGS
    -0.06
    POSITIVE LOGITS
    屏
    0.07
    =[]↵
    0.06
     nächsten
    0.06
     Anime
    0.06
     strengthens
    0.06
     nedost
    0.06
    ~↵↵
    0.06
    (BigInteger
    0.06
    .tipo
    0.06
    ClassName
    0.06
    Activations Density 0.031%

    No Known Activations