© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 126081
    Prev
    Next
    INDEX
    Explanations

    terms related to research and academic inquiry

    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
    kou
    -0.06
    itesse
    -0.06
    agon
    -0.06
    aque
    -0.06
    if
    -0.06
    upal
    -0.06
    phy
    -0.06
    itory
    -0.06
    oug
    -0.06
    atology
    -0.06
    POSITIVE LOGITS
    Gate
    0.08
     addCriterion
    0.07
    è£ģ
    0.07
    fund
    0.07
    [".
    0.07
    estatus
    0.07
    /Runtime
    0.06
    æķ¬
    0.06
    StrictEqual
    0.06
    -Mail
    0.06
    Activations Density 0.011%

    No Known Activations