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. 86055
    Prev
    Next
    INDEX
    Explanations

    Permission

    np_max-act · gemini-2.0-flash

    This neuron activates on the “Permission is granted…” clause in software license headers.

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

    code snippets and references related to collision detection algorithms.

    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
     rallied
    -0.07
    _has
    -0.07
    RR
    -0.06
    ής
    -0.06
    ,args
    -0.06
     فنی
    -0.06
     Hwy
    -0.06
    &nbsp
    -0.06
    ывания
    -0.06
    गर
    -0.06
    POSITIVE LOGITS
    可能
    0.07
    .tencent
    0.07
     Honestly
    0.06
    _snap
    0.06
     TIFF
    0.06
    Reminder
    0.06
    ça
    0.06
     showcasing
    0.06
     örg
    0.06
    -bottom
    0.06
    Activations Density 0.001%

    No Known Activations