© 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. 110295
    Prev
    Next
    INDEX
    Explanations

    Asking questions

    np_max-act · gemini-2.0-flash

    The neuron fires on phrasing that asks how to refine or improve prompts—e.g. requests for “more precise” or “more useful” questions to get better answers.

    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
     wireless
    -0.07
     코드
    -0.06
     OrderedDict
    -0.06
     hunts
    -0.06
     fort
    -0.06
    Ja
    -0.06
    usement
    -0.06
    .assertIsInstance
    -0.06
     hel
    -0.06
    871
    -0.06
    POSITIVE LOGITS
     Üy
    0.07
     берег
    0.07
     iff
    0.07
    ={"/
    0.06
     �
    0.06
     enzym
    0.06
    appro
    0.06
    姿
    0.06
    ','#
    0.06
     название
    0.06
    Activations Density 0.028%

    No Known Activations