© 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. 15-LLAMASCOPE-RES-131K
    11. 88402
    Prev
    Next
    INDEX
    Explanations

    specific numerical and statistical information

    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
    unit
    -0.07
    iben
    -0.06
    igma
    -0.06
    о
    -0.06
    imas
    -0.06
     Sly
    -0.06
    ãĥ³ãĥĨ
    -0.06
    eryl
    -0.06
    evi
    -0.06
    é¦Ļ
    -0.06
    POSITIVE LOGITS
    ãĥ¡ãĥ©
    0.07
    topl
    0.06
     ANT
    0.06
     coop
    0.06
    lash
    0.06
    æŃ¯
    0.06
    atron
    0.06
    _ak
    0.06
    LAY
    0.06
    ledon
    0.06
    Activations Density 0.426%

    No Known Activations