© 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. 40859
    Prev
    Next
    INDEX
    Explanations

    references to product specifications and comparisons

    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
    strup
    -0.07
    aise
    -0.06
     hel
    -0.06
     becoming
    -0.06
     acts
    -0.06
    ariat
    -0.06
    herits
    -0.06
    à¥Ĥह
    -0.06
     slou
    -0.05
    _LT
    -0.05
    POSITIVE LOGITS
     contain
    0.14
     contains
    0.13
    contain
    0.12
     containing
    0.11
    contains
    0.11
     chứa
    0.10
     ÑģодеÑĢж
    0.10
     داراÛĮ
    0.10
     Contains
    0.10
    Contains
    0.10
    Activations Density 0.055%

    No Known Activations