© 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. 15-LLAMASCOPE-RES-131K
    11. 88182
    Prev
    Next
    INDEX
    Explanations

    structured data formats or syntax elements in written content

    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
     flesh
    -0.06
    -pos
    -0.06
     imp
    -0.06
    acific
    -0.06
    EVER
    -0.06
     dev
    -0.06
    imp
    -0.06
    pos
    -0.06
     devil
    -0.06
     pos
    -0.06
    POSITIVE LOGITS
    mnop
    0.07
    _observer
    0.07
    LEMENT
    0.06
     outra
    0.06
    ît
    0.06
    ÑģÑĮого
    0.06
     other
    0.06
    atrix
    0.06
    itia
    0.06
     Barg
    0.06
    Activations Density 0.015%

    No Known Activations