© 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. 4123
    Prev
    Next
    INDEX
    Explanations

    references to historical records and biographical details

    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
    -plus
    -0.07
     literally
    -0.07
    OLUM
    -0.07
     simply
    -0.07
    rott
    -0.06
    ampie
    -0.06
    æĻ¶
    -0.06
     partager
    -0.06
    ÏĥÏĦά
    -0.06
     eyeb
    -0.06
    POSITIVE LOGITS
     "[
    0.07
    ô
    0.07
    ì§ģ
    0.07
     ca
    0.07
    ÙĪع
    0.06
     recieved
    0.06
    ore
    0.06
    ċ
    0.06
    icit
    0.06
    unny
    0.06
    Activations Density 0.015%

    No Known Activations