© 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. 40877
    Prev
    Next
    INDEX
    Explanations

    numeric ratings and elements related to film reviews

    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
    wiÄħ
    -0.07
     (
    -0.06
    ork
    -0.06
     Gold
    -0.06
     Sor
    -0.06
    ide
    -0.06
     Petty
    -0.06
    ↵
    -0.06
    -m
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.10
    _Tis
    0.08
    /XMLSchema
    0.08
    #af
    0.08
    DisplayStyle
    0.08
    ãģªãģĮ
    0.07
    UsageId
    0.07
    ëŁ
    0.07
    /Area
    0.07
    оÑĩки
    0.07
    Activations Density 0.001%

    No Known Activations