© 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. 15-LLAMASCOPE-RES-131K
    11. 61485
    Prev
    Next
    INDEX
    Explanations

    numerical values and ratios

    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
    ãģ£ãģį
    -0.08
    еÑĢи
    -0.07
    rias
    -0.07
    еÑĢÑĸ
    -0.07
    medi
    -0.07
    forth
    -0.07
    rys
    -0.07
    ©
    -0.07
    utenberg
    -0.07
    kami
    -0.07
    POSITIVE LOGITS
     ratio
    0.09
    ratio
    0.09
     Ratio
    0.07
     ratios
    0.07
     odds
    0.06
    entrant
    0.06
    ystick
    0.06
    Ratio
    0.06
    _ratio
    0.06
    //{{
    0.06
    Activations Density 0.027%

    No Known Activations