© 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. 9-LLAMASCOPE-RES-131K
    11. 97626
    Prev
    Next
    INDEX
    Explanations

    mentions of companies and company-related terms

    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
    ilim
    -0.08
    ypse
    -0.07
    اÙĪر
    -0.07
    uese
    -0.06
    rah
    -0.06
     ?>"/>↵
    -0.06
    mae
    -0.06
    486
    -0.06
    186
    -0.06
    446
    -0.06
    POSITIVE LOGITS
    ãĥ«ãĥķ
    0.07
    ॰
    0.07
    ãģ¬
    0.06
    ences
    0.06
    uffman
    0.06
    gba
    0.06
    lund
    0.06
    ipples
    0.06
    ipple
    0.06
    asing
    0.06
    Activations Density 0.002%

    No Known Activations