© 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. 105518
    Prev
    Next
    INDEX
    Explanations

    phrases or contexts involving points scored in sports

    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
    ToFit
    -0.09
    PÅĻi
    -0.09
    ieee
    -0.07
    ì¸
    -0.07
     stret
    -0.07
    PÅĻÃŃ
    -0.07
    ascimento
    -0.07
    adol
    -0.07
    ëł´
    -0.07
    wyn
    -0.07
    POSITIVE LOGITS
     three
    0.07
    no
    0.07
     overall
    0.06
     two
    0.06
    zing
    0.06
    aid
    0.06
     zero
    0.06
     commend
    0.06
     six
    0.06
     four
    0.06
    Activations Density 0.010%

    No Known Activations