© 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. 118671
    Prev
    Next
    INDEX
    Explanations

    references to online platforms and sources

    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
    obre
    -0.07
    /Runtime
    -0.06
    etat
    -0.06
    ÏĦεÏį
    -0.06
    iltr
    -0.06
    eous
    -0.06
    innie
    -0.06
    ваÑĤ
    -0.06
    etak
    -0.06
    اÙĪ
    -0.06
    POSITIVE LOGITS
    adan
    0.08
    ï¸ı
    0.07
    oly
    0.06
    rott
    0.06
    ford
    0.06
    anked
    0.06
     adr
    0.06
    dorf
    0.06
    bens
    0.06
    ucz
    0.06
    Activations Density 0.006%

    No Known Activations