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. 130212
    Prev
    Next
    INDEX
    Explanations

    Technical documents

    np_max-act · gemini-2.0-flash

    This neuron responds to terms naming laboratory sampling or specimen‐processing methods (e.g. venipuncture, swab, pipette, centrifugation).

    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
    .epoch
    -0.06
     Yale
    -0.06
    .uk
    -0.06
    _batches
    -0.06
    ecome
    -0.06
    ريكي
    -0.06
     (~
    -0.06
     �
    -0.06
    /the
    -0.06
    Phil
    -0.06
    POSITIVE LOGITS
     вне
    0.06
    金属
    0.06
    '];↵↵
    0.06
     },
    0.06
     العديد
    0.06
    [int
    0.06
    ส
    0.06
    ์↵↵
    0.06
     difer
    0.06
    AreaView
    0.06
    Activations Density 0.178%

    No Known Activations