© 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. 129048
    Prev
    Next
    INDEX
    Explanations

    references to mathematics and mathematical concepts

    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
    adge
    -0.07
    stå
    -0.07
    heat
    -0.07
    heiten
    -0.07
    ector
    -0.07
    lass
    -0.07
    gle
    -0.06
    ehen
    -0.06
    olumn
    -0.06
    rowsable
    -0.06
    POSITIVE LOGITS
    ematic
    0.13
    ieu
    0.12
    ematics
    0.12
    ematik
    0.10
    ilda
    0.09
    ilde
    0.08
    aniel
    0.08
    matic
    0.08
    fully
    0.08
    letes
    0.08
    Activations Density 0.056%

    No Known Activations