© 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. 124589
    Prev
    Next
    INDEX
    Explanations

    mentions of pilot projects and related trials

    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
     structures
    -0.06
     interp
    -0.06
    buch
    -0.06
    aticon
    -0.06
     satellite
    -0.06
    átek
    -0.06
    .Des
    -0.06
    illac
    -0.06
     positions
    -0.05
     worms
    -0.05
    POSITIVE LOGITS
     trial
    0.13
     test
    0.13
     experimental
    0.12
     experiment
    0.11
     testing
    0.11
     thá»Ń
    0.11
     pilot
    0.11
     trials
    0.11
    trial
    0.11
    experimental
    0.10
    Activations Density 0.024%

    No Known Activations