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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75375
    Prev
    Next
    INDEX
    Explanations

    references to various types of media content and technical specifications

    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
    ,
    -0.07
    kee
    -0.06
    onen
    -0.06
    SEP
    -0.06
    -
    -0.06
    oons
    -0.05
     satur
    -0.05
    @student
    -0.05
    عات
    -0.05
     or
    -0.05
    POSITIVE LOGITS
    第
    0.11
     第
    0.10
     ìĭľì¦Į
    0.09
    ilden
    0.08
    ancia
    0.07
     Episode
    0.07
    'gc
    0.07
    ingleton
    0.07
    dech
    0.07
    adil
    0.07
    Activations Density 0.011%

    No Known Activations