© 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. 29127
    Prev
    Next
    INDEX
    Explanations

    references to errors or issues related to information accuracy

    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
    orsche
    -0.06
    oyo
    -0.06
    leted
    -0.06
    /goto
    -0.06
    emodel
    -0.06
    ogle
    -0.06
    elik
    -0.06
     caption
    -0.06
    å£
    -0.06
    ewis
    -0.06
    POSITIVE LOGITS
    elm
    0.07
    trinsic
    0.06
    Äħd
    0.06
    acher
    0.06
    _delivery
    0.06
    ÃŃrk
    0.06
     Pony
    0.06
     lost
    0.06
    flake
    0.06
    .delivery
    0.06
    Activations Density 0.001%

    No Known Activations