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. 86035
    Prev
    Next
    INDEX
    Explanations

    endoplasmic reticulum

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the (endo- or sarco-)plasmic reticulum subcellular compartment.

    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
     losses
    -0.06
     Kons
    -0.06
     paypal
    -0.06
     những
    -0.06
     далеко
    -0.06
     warped
    -0.06
     брос
    -0.06
     numbers
    -0.06
     میدان
    -0.06
     pockets
    -0.06
    POSITIVE LOGITS
    rand
    0.08
    pillar
    0.08
     Trần
    0.07
    (word
    0.07
    art
    0.07
     Wein
    0.07
    lant
    0.06
    ence
    0.06
     auth
    0.06
    _IND
    0.06
    Activations Density 0.001%

    No Known Activations