© 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. 128380
    Prev
    Next
    INDEX
    Explanations

    references to orbits or orbital mechanics

    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
    agers
    -0.08
    etch
    -0.08
    ager
    -0.07
    plier
    -0.07
    antage
    -0.07
    rava
    -0.07
    edom
    -0.07
    gere
    -0.06
    fld
    -0.06
    ows
    -0.06
    POSITIVE LOGITS
    ing
    0.11
    ally
    0.07
    als
    0.07
    acular
    0.07
    olog
    0.07
    tl
    0.07
    ale
    0.07
    à¥įतà¤ķ
    0.07
    antan
    0.07
    ant
    0.06
    Activations Density 0.004%

    No Known Activations