© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 76395
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash

    Sentences that begin an answer post written in the first person (e.g., the start of an "A:" response where the author says "I" or "I think").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ela
    -0.07
    给我
    -0.07
    ternal
    -0.07
    erialization
    -0.06
    -aut
    -0.06
    _vector
    -0.06
    emale
    -0.06
    Language
    -0.06
    .prop
    -0.06
    SHORT
    -0.06
    POSITIVE LOGITS
     FAQ
    0.06
     Indones
    0.06
    :http
    0.06
    :^(
    0.06
     시
    0.06
     örgüt
    0.06
     полос
    0.06
     extends
    0.06
     REPL
    0.06
     Güven
    0.06
    Activations Density 0.034%

    No Known Activations