Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4993
    Prev
    Next
    INDEX
    Explanations

    references to specific SF (science fiction) variations or 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
    aison
    -0.08
    tica
    -0.07
    еÑģи
    -0.07
    l
    -0.07
    attice
    -0.07
    058
    -0.07
    ulus
    -0.06
    verse
    -0.06
    ambique
    -0.06
    iedy
    -0.06
    POSITIVE LOGITS
    etched
    0.07
     sf
    0.07
     SF
    0.07
     Buen
    0.07
    sted
    0.06
    _mex
    0.06
    KeySpec
    0.06
    iation
    0.06
     Mime
    0.06
    RenderWindow
    0.06
    Activations Density 0.007%

    No Known Activations