© 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. 17-LLAMASCOPE-RES-131K
    11. 58759
    Prev
    Next
    INDEX
    Explanations

    references to business or organizational entities and associated identifiers

    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
    taire
    -0.07
    YG
    -0.07
    orsi
    -0.07
    amilia
    -0.07
    _charset
    -0.06
    alyzer
    -0.06
    ableViewController
    -0.06
    lsi
    -0.06
     sâu
    -0.06
     flats
    -0.06
    POSITIVE LOGITS
    makers
    0.07
    865
    0.07
    nee
    0.06
     America
    0.06
    855
    0.06
    dba
    0.06
     Nightmare
    0.06
     gridColumn
    0.06
    UTTON
    0.06
    aos
    0.06
    Activations Density 0.008%

    No Known Activations