© 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. 15-LLAMASCOPE-RES-131K
    11. 87312
    Prev
    Next
    INDEX
    Explanations

    scientific references and citations within academic texts

    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
    ake
    -0.07
    iper
    -0.07
    ITTLE
    -0.07
    ittle
    -0.06
    abi
    -0.06
    yg
    -0.06
    ENDOR
    -0.06
    iland
    -0.06
    rt
    -0.06
    END
    -0.06
    POSITIVE LOGITS
    riott
    0.06
    _expiry
    0.06
    ivated
    0.06
    اÛĮÙĩ
    0.06
    ated
    0.06
    -webpack
    0.06
    Elite
    0.06
    PIO
    0.06
    etCode
    0.06
    elop
    0.06
    Activations Density 0.001%

    No Known Activations