© 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. 88545
    Prev
    Next
    INDEX
    Explanations

    references to centers or hubs of activity and resources

    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
    -webpack
    -0.07
    apor
    -0.07
    'gc
    -0.07
    лÑĥÑĩ
    -0.07
    orie
    -0.07
    ùy
    -0.07
    aret
    -0.07
    gan
    -0.07
    hled
    -0.07
    oder
    -0.07
    POSITIVE LOGITS
     of
    0.08
    around
    0.07
    punkt
    0.06
    htable
    0.06
     hub
    0.06
     around
    0.06
     for
    0.06
    avanaugh
    0.06
    ference
    0.06
    for
    0.06
    Activations Density 0.016%

    No Known Activations