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. 85883
    Prev
    Next
    INDEX
    Explanations

    ard

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of Grignard reagents (e.g. “Grignard reagent”) and related magnesium‐based reagent terms.

    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
     hầu
    -0.06
     Kem
    -0.06
     Tep
    -0.06
     CIF
    -0.06
     Ky
    -0.06
    िष
    -0.06
    /at
    -0.06
    .ServletException
    -0.06
    clr
    -0.06
     PY
    -0.06
    POSITIVE LOGITS
     о
    0.07
    報告
    0.07
    $input
    0.07
     senators
    0.07
    matter
    0.07
     formData
    0.07
     Craft
    0.07
    OrDefault
    0.07
     shortfall
    0.07
     sais
    0.07
    Activations Density 0.001%

    No Known Activations