© 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. 78899
    Prev
    Next
    INDEX
    Explanations

    questions and requests for help related to technical issues

    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
    .MaxLength
    -0.06
    .bat
    -0.06
    omin
    -0.06
    cean
    -0.06
    jun
    -0.06
     Stam
    -0.05
     éĻIJ
    -0.05
    arters
    -0.05
     ext
    -0.05
    un
    -0.05
    POSITIVE LOGITS
     proper
    0.09
     properly
    0.09
     Proper
    0.08
    proper
    0.08
    zek
    0.08
    ÙħÛĮÙĨ
    0.07
    cing
    0.07
     fix
    0.07
    æŃ£ç¡®
    0.07
     longer
    0.07
    Activations Density 0.008%

    No Known Activations