Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5325
    Prev
    Next
    INDEX
    Explanations

    words related to indigenous culture and heritage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERCHANT
    -0.08
    olik
    -0.08
    togroup
    -0.07
    hiba
    -0.07
    eneg
    -0.07
    ington
    -0.07
    idges
    -0.07
    anteed
    -0.07
    okies
    -0.07
    idge
    -0.07
    POSITIVE LOGITS
     Gür
    0.07
    ãģ¡ãĤĥ
    0.06
    /system
    0.06
    esh
    0.06
    awi
    0.06
    ius
    0.06
    /System
    0.06
    toupper
    0.06
    icros
    0.06
    115
    0.05
    Activations Density 0.001%

    No Known Activations