© 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. 125220
    Prev
    Next
    INDEX
    Explanations

    references to significant artistic works and their descriptions

    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
    .story
    -0.07
    hir
    -0.07
    ascus
    -0.07
    structor
    -0.06
    ê»ĺ
    -0.06
    ObjectType
    -0.06
     withObject
    -0.06
    rica
    -0.06
    hs
    -0.06
    اÙĨÙĪ
    -0.06
    POSITIVE LOGITS
     of
    0.08
    ijke
    0.07
    inded
    0.07
    ives
    0.07
     Nacht
    0.06
     entirety
    0.06
    lixir
    0.06
    olla
    0.06
    dispose
    0.06
    (s
    0.06
    Activations Density 0.021%

    No Known Activations