© 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. 106545
    Prev
    Next
    INDEX
    Explanations

    references to "Cedar" in various contexts

    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
    e
    -0.09
    t
    -0.09
    جاÙĨ
    -0.07
    i
    -0.06
    kg
    -0.06
    AllowAnonymous
    -0.06
    y
    -0.06
    917
    -0.06
    isans
    -0.06
     vir
    -0.06
    POSITIVE LOGITS
    idlo
    0.08
     Dün
    0.07
    lea
    0.07
    holm
    0.07
    burg
    0.07
    udeau
    0.07
    äter
    0.07
    mere
    0.07
    brook
    0.07
     republika
    0.07
    Activations Density 0.003%

    No Known Activations