© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43302
    Prev
    Next
    INDEX
    Explanations

    expressing opinions

    np_max-act · gemini-2.0-flash

    The neuron fires on subjective or evaluative words that express opinion, judgment, or emotional reaction.

    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
    <f
    -0.07
     oku
    -0.07
    ember
    -0.07
    .findBy
    -0.06
    르고
    -0.06
    xima
    -0.06
    861
    -0.06
    Nullable
    -0.06
    Shows
    -0.06
     joke
    -0.06
    POSITIVE LOGITS
    .auto
    0.07
     pequ
    0.06
     chlap
    0.06
    代
    0.06
     ارتف
    0.06
     moderation
    0.06
     Alleg
    0.06
     동일
    0.06
     Кри
    0.06
     Fiber
    0.06
    Activations Density 0.032%

    No Known Activations