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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 85923
    Prev
    Next
    INDEX
    Explanations

    technical measurements

    np_max-act · gemini-2.0-flash

    This neuron detects numbered measurement positions (e.g., “Pos 1,” “Pos 2,” etc.) in the experimental methods section.

    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
     collateral
    -0.06
    Norm
    -0.06
     thải
    -0.06
     Yine
    -0.06
     ALOG
    -0.06
    Fal
    -0.06
    INFO
    -0.06
    PX
    -0.06
    퇴
    -0.06
    HSV
    -0.06
    POSITIVE LOGITS
    };
    0.07
    توبر
    0.06
    :Register
    0.06
     northeast
    0.06
    ंस
    0.06
    owany
    0.06
    arn
    0.06
    organic
    0.06
    ايت
    0.06
    creative
    0.06
    Activations Density 0.188%

    No Known Activations