© 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. 93804
    Prev
    Next
    INDEX
    Explanations

    references to scientific or technical processes and terminology

    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
    uno
    -0.08
    å§Ķ
    -0.07
    ë¬¸ìłľ
    -0.07
    代çIJĨ
    -0.07
    BOR
    -0.07
    lej
    -0.07
    pta
    -0.07
    ndl
    -0.06
    _RETRY
    -0.06
    ubber
    -0.06
    POSITIVE LOGITS
    .tw
    0.06
    348
    0.06
    349
    0.06
     rol
    0.06
     Rad
    0.06
    /repository
    0.06
    ank
    0.05
    ru
    0.05
    215
    0.05
     sore
    0.05
    Activations Density 0.001%

    No Known Activations