© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118071
    Prev
    Next
    INDEX
    Explanations

    references to natural elements and their properties

    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
    cÃŃ
    -0.06
    .inverse
    -0.06
    obe
    -0.06
     skoro
    -0.06
    cors
    -0.06
     pÅĻep
    -0.06
    olumn
    -0.06
     mắt
    -0.06
    apus
    -0.06
    .fits
    -0.06
    POSITIVE LOGITS
     signature
    0.09
     patterns
    0.09
    signature
    0.08
     changes
    0.08
     signatures
    0.07
     pattern
    0.07
    -pattern
    0.07
    .pattern
    0.07
    indh
    0.07
     certain
    0.07
    Activations Density 0.022%

    No Known Activations