© 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. 83366
    Prev
    Next
    INDEX
    Explanations

    actions related to obtaining or accessing information and resources online

    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
    anmar
    -0.06
     Mug
    -0.06
     Grip
    -0.06
    apl
    -0.06
    odor
    -0.06
    afe
    -0.06
    æĸĹ
    -0.06
     compilers
    -0.06
    enor
    -0.06
    lic
    -0.05
    POSITIVE LOGITS
    xEE
    0.07
    佩
    0.07
    íĨµ
    0.07
    idity
    0.07
    asal
    0.07
    Defaults
    0.07
    ULA
    0.07
    emachine
    0.07
    شاÙĨ
    0.06
    лег
    0.06
    Activations Density 0.000%

    No Known Activations