© 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. 106287
    Prev
    Next
    INDEX
    Explanations

    references to high-profile individuals or events

    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
    ikel
    -0.08
    ReturnType
    -0.08
    \CMS
    -0.07
    onya
    -0.07
    chop
    -0.07
    ards
    -0.07
    riot
    -0.07
    кеÑĤ
    -0.07
    ideos
    -0.07
    gv
    -0.07
    POSITIVE LOGITS
    /high
    0.10
    /pop
    0.08
    人çī©
    0.06
    âĢĮترÛĮÙĨ
    0.06
    eous
    0.06
    aus
    0.06
    ography
    0.06
    -low
    0.06
     public
    0.06
    /power
    0.06
    Activations Density 0.004%

    No Known Activations