© 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. 81655
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data communication protocols

    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
     leadership
    -0.06
    iam
    -0.06
    638
    -0.06
     Gateway
    -0.06
    outh
    -0.06
    lob
    -0.06
    bish
    -0.06
    ateway
    -0.06
    è§Ĵ
    -0.06
    anova
    -0.06
    POSITIVE LOGITS
     actual
    0.11
     main
    0.10
     Actual
    0.10
    Actual
    0.10
    actual
    0.09
     ìĭ¤ìłľ
    0.09
     substantive
    0.09
     actually
    0.08
    _main
    0.08
    elter
    0.08
    Activations Density 0.050%

    No Known Activations