© 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. 129480
    Prev
    Next
    INDEX
    Explanations

    details related to game statistics and player performance

    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
    ereum
    -0.07
    zell
    -0.06
    ι
    -0.06
    -mf
    -0.06
     hemisphere
    -0.06
    .attach
    -0.06
    ÑĥÑĪ
    -0.06
     Kaynak
    -0.06
    ayers
    -0.06
     consumer
    -0.06
    POSITIVE LOGITS
     earlier
    0.08
     later
    0.07
    Ïģγ
    0.07
     Robbins
    0.07
    ÎŃλ
    0.07
    orden
    0.06
     später
    0.06
    afür
    0.06
     chiếc
    0.06
    .selenium
    0.06
    Activations Density 0.016%

    No Known Activations