© 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. 70918
    Prev
    Next
    INDEX
    Explanations

    positive feedback and recommendations about individual service providers

    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
    edBy
    -0.06
     surf
    -0.06
     Lair
    -0.06
     meaning
    -0.05
    angu
    -0.05
     estate
    -0.05
     Yours
    -0.05
     Pier
    -0.05
     med
    -0.05
    65
    -0.05
    POSITIVE LOGITS
    BorderStyle
    0.08
    umer
    0.08
    atel
    0.08
     ÐŁÐ¾Ðº
    0.07
    eÅŁ
    0.07
    OLON
    0.07
    aru
    0.07
    SizePolicy
    0.07
    _EMIT
    0.07
    ีย
    0.07
    Activations Density 0.020%

    No Known Activations