© 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. 58622
    Prev
    Next
    INDEX
    Explanations

    standalone punctuation marks 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
    fat
    -0.07
    sdale
    -0.07
    chg
    -0.07
    ÑĥÑĪка
    -0.06
    eman
    -0.06
    igor
    -0.06
    alter
    -0.06
    HEMA
    -0.06
     Ble
    -0.06
    utenberg
    -0.06
    POSITIVE LOGITS
     Wah
    0.06
    /tool
    0.06
     Hass
    0.06
    asl
    0.06
    aign
    0.06
     Setter
    0.06
    oron
    0.06
     Anh
    0.06
     bases
    0.06
     è¢
    0.06
    Activations Density 0.000%

    No Known Activations