© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87056
    Prev
    Next
    INDEX
    Explanations

    references to obtaining or accessing free content and services

    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
     Su
    -0.06
     Durch
    -0.06
    OrDefault
    -0.06
     Bol
    -0.06
    su
    -0.06
    ryn
    -0.06
    sm
    -0.06
    lah
    -0.05
    emi
    -0.05
     detr
    -0.05
    POSITIVE LOGITS
     ÙĪÙĦا
    0.07
    ALAR
    0.07
    вÑĸлÑĮ
    0.07
    .fre
    0.07
     Niet
    0.07
    oser
    0.07
    æŃ©
    0.07
    rieve
    0.06
    rup
    0.06
    -ves
    0.06
    Activations Density 0.010%

    No Known Activations