© 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. 17-LLAMASCOPE-RES-131K
    11. 62041
    Prev
    Next
    INDEX
    Explanations

    code-related markup languages and associated file types

    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
    ept
    -0.08
    tres
    -0.07
    eut
    -0.07
    eview
    -0.07
    ilda
    -0.07
    ekler
    -0.06
    peat
    -0.06
    ãĤ¯ãĥŃ
    -0.06
    INCLUDED
    -0.06
    ли
    -0.06
    POSITIVE LOGITS
     xmlns
    0.06
    _LS
    0.06
     lang
    0.06
    ár
    0.06
    .scene
    0.06
    ëĭĪìķĦ
    0.05
     Malk
    0.05
    "."
    0.05
    468
    0.05
    ega
    0.05
    Activations Density 0.001%

    No Known Activations