© 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. 17-LLAMASCOPE-RES-131K
    11. 127567
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

    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
    ç«ĭãģ¡
    -0.06
    ãĤ¤ãĤº
    -0.06
     Kanun
    -0.06
    elle
    -0.05
    muz
    -0.05
    WithContext
    -0.05
    ROP
    -0.05
    iesen
    -0.05
    ESIS
    -0.05
     Sala
    -0.05
    POSITIVE LOGITS
    uchi
    0.07
    laden
    0.07
    atos
    0.07
    ammers
    0.07
    frauen
    0.07
    pite
    0.07
    ÏĢλ
    0.06
    ина
    0.06
    eldorf
    0.06
    anes
    0.06
    Activations Density 0.081%

    No Known Activations