© 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. 82714
    Prev
    Next
    INDEX
    Explanations

    technical terms and options related to configuration settings

    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
    .Invariant
    -0.08
    idth
    -0.08
    noinspection
    -0.07
    ushima
    -0.07
    anchise
    -0.07
    eyse
    -0.07
    UILTIN
    -0.07
    cheid
    -0.07
    assen
    -0.07
    eldon
    -0.07
    POSITIVE LOGITS
     useful
    0.07
     Useful
    0.07
     otherwise
    0.07
     Note
    0.06
     false
    0.06
     False
    0.06
     note
    0.06
    heed
    0.06
     setting
    0.06
     This
    0.06
    Activations Density 0.042%

    No Known Activations