© 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. 105924
    Prev
    Next
    INDEX
    Explanations

    references to educational curricula and curriculum-related 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
    ness
    -0.08
    (er
    -0.07
    hood
    -0.07
    leigh
    -0.07
    fold
    -0.07
    lege
    -0.06
    bour
    -0.06
    bit
    -0.06
    fall
    -0.06
    liness
    -0.06
    POSITIVE LOGITS
     vitae
    0.17
     dÄ±ÅŁÄ±
    0.12
    cope
    0.09
    idth
    0.07
    icensed
    0.07
    oftware
    0.07
    /Instruction
    0.07
    adesh
    0.07
    //{{
    0.07
    ettings
    0.07
    Activations Density 0.007%

    No Known Activations