© 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 EvalsExportsinterp-engineNEWAPI 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. 86581
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistics

    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
    ãģĺ
    -0.08
    rael
    -0.08
    ajan
    -0.08
    à¹īาà¸ĩ
    -0.08
    ullo
    -0.08
    loys
    -0.08
    ÙĨÚ¯
    -0.07
    ãģ£ãģį
    -0.07
    ÑĮко
    -0.07
    unami
    -0.07
    POSITIVE LOGITS
    ãģ¤ãģ®
    0.08
    ï¸ı
    0.08
    th
    0.07
    yz
    0.07
    ens
    0.06
    atten
    0.06
    erez
    0.06
    een
    0.06
    eenth
    0.06
    ty
    0.06
    Activations Density 0.073%

    No Known Activations