© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 107853
    Prev
    Next
    INDEX
    Explanations

    references to diverse topics or experiences within a post

    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
     Insecta
    -0.08
    BUG
    -0.08
    odash
    -0.08
    fo
    -0.08
     Gros
    -0.07
    -translate
    -0.07
    _UDP
    -0.07
     ÙģرÙĪ
    -0.07
    ìŀ¬
    -0.07
     BUG
    -0.07
    POSITIVE LOGITS
    umann
    0.07
    ories
    0.07
    uft
    0.07
    ché
    0.06
     Herm
    0.06
     Hospitality
    0.06
    lice
    0.05
    orie
    0.05
     comm
    0.05
    rr
    0.05
    Activations Density 0.001%

    No Known Activations