© 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. 81574
    Prev
    Next
    INDEX
    Explanations

    references to groups or organizations

    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
     maybe
    -0.08
    utzer
    -0.07
    .GraphicsUnit
    -0.07
    ÛĮÙĩ
    -0.07
    uckle
    -0.07
    agini
    -0.07
    Ð®ÐĽ
    -0.06
     Wilkinson
    -0.06
    ayıp
    -0.06
    ostel
    -0.06
    POSITIVE LOGITS
     ↵
    0.07
    ited
    0.06
    afort
    0.06
    uthor
    0.06
    itti
    0.06
     Fasc
    0.05
    ahn
    0.05
    '
    0.05
     Junk
    0.05
    使çĶ¨
    0.05
    Activations Density 0.000%

    No Known Activations