© 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 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. 106718
    Prev
    Next
    INDEX
    Explanations

    references to items or entities that underwent significant changes or developments

    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
    .scalablytyped
    -0.10
    icaret
    -0.09
    |{↵
    -0.09
    ":[{↵
    -0.08
    ãģ¾ãģŁ
    -0.08
    ":""
    -0.08
    ordova
    -0.08
    ãĥ¼ãĥł
    -0.08
    afil
    -0.08
    iddet
    -0.08
    POSITIVE LOGITS
    ;
    0.13
     whereas
    0.10
     [];
    0.09
     followed
    0.08
     ìŀĪê³ł
    0.08
    )ãĢģ
    0.08
     ;
    0.08
    ),
    0.07
    ï¼īãĢģ
    0.07
     while
    0.07
    Activations Density 0.222%

    No Known Activations