© 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. 71330
    Prev
    Next
    INDEX
    Explanations

    references to educational programs and proposals

    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
    inka
    -0.07
    SDL
    -0.07
    ige
    -0.06
    reon
    -0.06
    pard
    -0.06
    obus
    -0.06
    PPER
    -0.06
    _consumer
    -0.06
    isko
    -0.06
     Instruments
    -0.06
    POSITIVE LOGITS
    panion
    0.08
    usercontent
    0.07
    icontrol
    0.07
     proposal
    0.07
     project
    0.07
     proje
    0.07
    .Compose
    0.07
    .zh
    0.07
    ToWorld
    0.07
    inea
    0.07
    Activations Density 0.001%

    No Known Activations