© 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. 15-LLAMASCOPE-RES-131K
    11. 88969
    Prev
    Next
    INDEX
    Explanations

    references to interactive elements or sections in a document

    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
    erson
    -0.08
    omens
    -0.07
    ç¨
    -0.07
    ocket
    -0.07
    ombre
    -0.07
    dain
    -0.06
    óm
    -0.06
    sob
    -0.06
    ebek
    -0.06
    æĸ
    -0.06
    POSITIVE LOGITS
     Copp
    0.06
     Sept
    0.06
    _TYPED
    0.06
     below
    0.06
    veis
    0.06
    361
    0.06
     @}
    0.06
     Brun
    0.06
    726
    0.05
     Q
    0.05
    Activations Density 0.001%

    No Known Activations