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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129432
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating assistance and support in various contexts

    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
    esson
    -0.08
    ouro
    -0.07
    steller
    -0.07
     totalPages
    -0.06
    apol
    -0.06
    uito
    -0.06
    erval
    -0.06
    icions
    -0.06
    ordo
    -0.06
    andbox
    -0.06
    POSITIVE LOGITS
    aden
    0.07
    anden
    0.06
    omm
    0.06
    alle
    0.06
    رÙĪÛĮ
    0.06
     authorised
    0.06
    гал
    0.06
     ÃĿ
    0.06
     STA
    0.06
     GÃľ
    0.06
    Activations Density 0.007%

    No Known Activations