© 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. 4945
    Prev
    Next
    INDEX
    Explanations

    numeric data likely related to dates or statistical information

    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
    idy
    -0.07
     kappa
    -0.07
    æķı
    -0.07
    .cz
    -0.07
    ,[],
    -0.07
    ĭ
    -0.07
     isSuccess
    -0.06
     Slut
    -0.06
    _ASSUME
    -0.06
     ÑĤоп
    -0.06
    POSITIVE LOGITS
    asher
    0.06
     Uncategorized
    0.06
    .
    0.06
     exponentially
    0.06
     others
    0.06
    tl
    0.06
     other
    0.05
     numberWith
    0.05
    ãĥĥãĤ«ãĥ¼
    0.05
    inae
    0.05
    Activations Density 0.012%

    No Known Activations