© 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. 53997
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    dialogues reflecting attitudes towards social topics and cultural comments.

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

    The neuron strongly activates on the question‐mark token (and related surrounding tokens), effectively detecting when the text is a question.

    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
     جمله
    -0.06
    conversation
    -0.06
    intage
    -0.06
     OVERRIDE
    -0.06
     Aly
    -0.06
     Server
    -0.06
    서
    -0.06
    ownload
    -0.06
     reluct
    -0.06
     guitars
    -0.06
    POSITIVE LOGITS
     چین
    0.07
    นก
    0.07
     dismay
    0.07
    ……。
    0.06
     <
    0.06
    )>=
    0.06
     Abb
    0.06
    !("{}",
    0.06
     opposing
    0.06
     irresist
    0.06
    Activations Density 0.036%

    No Known Activations