Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 110057
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash

    This neuron specializes in detecting numeric measurement 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
     Tk
    -0.07
     entrance
    -0.07
     pertaining
    -0.06
     fantasy
    -0.06
     &:
    -0.06
    .encrypt
    -0.06
    Granted
    -0.06
    anda
    -0.06
     exhaust
    -0.06
    Collision
    -0.06
    POSITIVE LOGITS
     ┃
    0.07
    .LA
    0.07
     fav
    0.07
    )","
    0.07
     fiat
    0.07
     scientifically
    0.07
     fod
    0.07
    =").
    0.07
    户
    0.07
    ΑΜ
    0.06
    Activations Density 0.034%

    No Known Activations