© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 62191
    Prev
    Next
    INDEX
    Explanations

    special formatting elements or sections within a structured document

    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
    keley
    -0.07
    iasi
    -0.06
    /problem
    -0.06
    blers
    -0.06
    oras
    -0.06
    ãĥĸãĥ©
    -0.06
    amble
    -0.06
    Äĥng
    -0.06
    íĥĪ
    -0.06
    pes
    -0.06
    POSITIVE LOGITS
    ÑĢоÑĪ
    0.07
    /apis
    0.07
    ">//
    0.06
    734
    0.06
    spiel
    0.06
    é½
    0.06
     MÃľ
    0.06
    (substr
    0.06
    ÐŁÑĸд
    0.06
    kir
    0.06
    Activations Density 0.035%

    No Known Activations