© 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. 106066
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to academic conferences and publications

    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
     ç²
    -0.06
     Pent
    -0.06
     Shadows
    -0.06
    ofil
    -0.06
    롱
    -0.06
    人们
    -0.06
    ogg
    -0.05
    STA
    -0.05
     nuts
    -0.05
    quan
    -0.05
    POSITIVE LOGITS
    aze
    0.06
    loys
    0.06
     Ammo
    0.06
    anity
    0.06
    ulton
    0.06
    otent
    0.06
    adders
    0.06
    auce
    0.06
    кол
    0.06
    ona
    0.06
    Activations Density 0.005%

    No Known Activations