© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43510
    Prev
    Next
    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash

    This neuron detects in‐text reference/citation markers (e.g. the “@”, “B”, and associated numeric identifiers used in bibliographic citations).

    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
     Somehow
    -0.07
     hail
    -0.06
     smear
    -0.06
     постоян
    -0.06
    Dam
    -0.06
    ПО
    -0.06
    吾
    -0.06
    corner
    -0.06
     VII
    -0.06
     Tyson
    -0.06
    POSITIVE LOGITS
    'app
    0.07
     Transformers
    0.07
     intrusive
    0.07
    .ค
    0.06
    Ệ
    0.06
    "/>.↵
    0.06
    atl
    0.06
    dál
    0.06
     insecurity
    0.06
    ").↵
    0.06
    Activations Density 0.009%

    No Known Activations