© 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. 9-LLAMASCOPE-RES-131K
    11. 98001
    Prev
    Next
    INDEX
    Explanations

    references to specific companies and their associated data or pages

    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
    peare
    -0.07
    ÑĢавилÑĮ
    -0.06
    ov
    -0.06
    villa
    -0.06
    tol
    -0.06
    -instance
    -0.06
    (æĹ¥
    -0.06
    èĨ
    -0.06
    ãĥĭãĤ¢
    -0.06
    olie
    -0.06
    POSITIVE LOGITS
    {{{
    0.07
    esses
    0.07
     åķĨ
    0.06
    scoped
    0.06
    ject
    0.06
    POR
    0.06
     íķµ
    0.06
     Phú
    0.06
     Rog
    0.06
    Scope
    0.06
    Activations Density 0.000%

    No Known Activations