© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 13501
    Prev
    Next
    INDEX
    Explanations

    enzyme subunits

    np_max-act · gemini-2.0-flash

    The neuron highlights numeric measurements and quantitative descriptors (e.g. molecular weights, subunit counts, pH values) in biochemical text.

    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
    ظه
    -0.06
    itempty
    -0.06
     validations
    -0.06
    .fontSize
    -0.06
    _put
    -0.06
     Osw
    -0.06
    工具
    -0.06
     Clothes
    -0.06
     Photoshop
    -0.06
    Ef
    -0.06
    POSITIVE LOGITS
     depends
    0.08
     affecting
    0.07
    τιο
    0.07
    يا
    0.07
     enjoy
    0.07
     THAN
    0.06
     tempor
    0.06
     kan
    0.06
     березня
    0.06
     sponsorship
    0.06
    Activations Density 0.015%

    No Known Activations