© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 368
    Prev
    Next
    INDEX
    Explanations

    symbols or characters indicating special events or promotions

    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
    annel
    -0.07
    asso
    -0.07
    olate
    -0.07
    اکÛĮ
    -0.07
    lac
    -0.07
    ispiel
    -0.06
    ANTE
    -0.06
    ihan
    -0.06
    zcze
    -0.06
    icians
    -0.06
    POSITIVE LOGITS
    ativ
    0.06
    avers
    0.06
    ird
    0.06
    èİī
    0.05
     Sentinel
    0.05
    imal
    0.05
     Clarkson
    0.05
     _
    0.05
    /trunk
    0.05
     unity
    0.05
    Activations Density 0.003%

    No Known Activations