© 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. 6345
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects numeric or numeric-like tokens (especially floating‐point numbers).

    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
     PTSD
    -0.07
    �
    -0.07
     bunların
    -0.06
    intro
    -0.06
     Monk
    -0.06
    (pair
    -0.06
     Starbucks
    -0.06
     AST
    -0.06
    Ein
    -0.06
    FPS
    -0.06
    POSITIVE LOGITS
    μένα
    0.07
     disappearance
    0.07
     libr
    0.07
    .sum
    0.06
    idency
    0.06
    xbd
    0.06
     retorn
    0.06
     cuanto
    0.06
    ):
    0.06
     여자
    0.06
    Activations Density 0.008%

    No Known Activations