© 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. 16046
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical or scientific constructs and contributions

    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
    turnstile
    -0.07
    ãĤĩ
    -0.07
     Reich
    -0.06
    ungle
    -0.06
    ampa
    -0.06
    vak
    -0.06
    vou
    -0.06
    dou
    -0.06
    ().'/
    -0.06
    harma
    -0.06
    POSITIVE LOGITS
     contribution
    0.15
     contributions
    0.14
     Contribution
    0.12
     component
    0.11
     contributed
    0.11
     Contributions
    0.11
    contrib
    0.11
     components
    0.10
     contrib
    0.10
     componente
    0.10
    Activations Density 0.230%

    No Known Activations