© 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. 105072
    Prev
    Next
    INDEX
    Explanations

    punctuations and formatting elements in the text

    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
    ister
    -0.07
    erville
    -0.06
    åĪ©
    -0.06
     sway
    -0.06
     pickup
    -0.06
    ISTER
    -0.06
     blink
    -0.06
     Synopsis
    -0.06
     ÑģпоÑĢ
    -0.06
    bum
    -0.06
    POSITIVE LOGITS
     Uncategorized
    0.08
    _exempt
    0.07
    getc
    0.06
    ī
    0.06
    implify
    0.06
    TestId
    0.06
    ån
    0.06
    (Self
    0.06
    Labels
    0.06
    ailles
    0.06
    Activations Density 0.003%

    No Known Activations