© 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. 9-LLAMASCOPE-RES-131K
    11. 94861
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court cases

    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
     оÑģÑĤан
    -0.07
    ibri
    -0.06
    abase
    -0.06
    ongo
    -0.06
    itel
    -0.06
    visor
    -0.06
    irl
    -0.06
    apel
    -0.06
    astro
    -0.06
    .opendaylight
    -0.06
    POSITIVE LOGITS
    spb
    0.07
    owitz
    0.07
    anse
    0.07
    zon
    0.06
    ellas
    0.06
    onse
    0.06
     geil
    0.06
    à¥įमà¤ķ
    0.06
    CRM
    0.06
    .codec
    0.06
    Activations Density 0.006%

    No Known Activations