© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 93483
    Prev
    Next
    INDEX
    Explanations

    specific linguistic structures and terms related to indigenous communities and cultural elements

    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
    Hang
    -0.07
    izando
    -0.07
    ÑģÑĤав
    -0.07
    enz
    -0.06
    (#
    -0.06
    Ùijا
    -0.06
     veg
    -0.06
    ãĢģ“
    -0.06
    ichten
    -0.06
    .checkBox
    -0.06
    POSITIVE LOGITS
    ↵
    0.06
    ean
    0.06
    ept
    0.06
    hawks
    0.06
    /Web
    0.06
     mistakenly
    0.06
    BOOLE
    0.06
    itis
    0.06
    #End
    0.06
    ;element
    0.06
    Activations Density 0.032%

    No Known Activations