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. 16156
    Prev
    Next
    INDEX
    Explanations

    transporters

    np_max-act · gemini-2.0-flash

    terms related to glucose transport and metabolism, particularly as they relate to cellular functions and disorders.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects mentions of biological transport proteins (e.g. “transport,” “transporter,” “transporters”), especially nutrient transporters like glucose transporters.

    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
     DAY
    -0.06
     Eye
    -0.06
    �
    -0.06
    ))-
    -0.06
    描
    -0.06
    hire
    -0.06
     Gan
    -0.06
    _HDR
    -0.06
    Mu
    -0.06
     Pamela
    -0.06
    POSITIVE LOGITS
     dostate
    0.07
     mình
    0.07
    (@"
    0.06
     cơm
    0.06
    (serializer
    0.06
     OSS
    0.06
    自己
    0.06
    ้าง
    0.06
    <dd
    0.06
    thank
    0.06
    Activations Density 0.007%

    No Known Activations