© 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. 15701
    Prev
    Next
    INDEX
    Explanations

    references to specific players and their performance in sports contexts

    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
    .intellij
    -0.07
    ierz
    -0.06
    é¦
    -0.06
    λÏį
    -0.06
     boo
    -0.06
    amide
    -0.06
    ipop
    -0.06
    AGMA
    -0.06
    ehr
    -0.06
    itol
    -0.06
    POSITIVE LOGITS
    .man
    0.07
    marsh
    0.07
    .optimizer
    0.06
    åĭ¢
    0.06
    igram
    0.06
    UnitTest
    0.06
    ï½¥
    0.06
    NECT
    0.06
    اة
    0.06
    793
    0.06
    Activations Density 0.030%

    No Known Activations