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. 86034
    Prev
    Next
    INDEX
    Explanations

    <T

    np_max-act · gemini-2.0-flash

    The neuron fires on generic‐type syntax (e.g. the “<T>” tokens) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    discussions around custom collection classes and their behaviors, particularly in the context of serialization and event handling in programming.

    oai_token-act-pair · gpt-4o-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
    Her
    -0.07
    .flow
    -0.07
     некоторых
    -0.07
    ------------------------------------------------
    -0.07
    werk
    -0.06
     importantes
    -0.06
     serpent
    -0.06
    Wik
    -0.06
    Wall
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     }));↵↵
    0.06
     Eternal
    0.06
     Additional
    0.06
     rubbish
    0.06
    isEmpty
    0.06
    (subject
    0.06
     marched
    0.06
    TimeString
    0.05
     retreat
    0.05
    wingConstants
    0.05
    Activations Density 0.004%

    No Known Activations