© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92378
    Prev
    Next
    INDEX
    Explanations

    Guid

    np_max-act · gemini-2.0-flash

    The neuron detects GUID strings (the familiar 8-4-4-4-12 hexadecimal pattern enclosed in braces).

    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
    กระ
    -0.08
    ole
    -0.08
    orts
    -0.08
    illa
    -0.08
    erte
    -0.07
    ashes
    -0.07
    HE
    -0.07
    enco
    -0.07
    house
    -0.07
    ْر
    -0.07
    POSITIVE LOGITS
     Guid
    0.08
    Guid
    0.08
     fid
    0.07
     Wed
    0.07
     Wisconsin
    0.07
    UID
    0.07
     openid
    0.07
     strokeWidth
    0.07
    fid
    0.07
     GUID
    0.07
    Activations Density 0.005%

    No Known Activations