© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 72005
    Prev
    Next
    INDEX
    Explanations

    dates and times related information

    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
    ages
    -0.06
    asta
    -0.06
    Ø·ÙĬ
    -0.06
    u
    -0.06
    itch
    -0.06
    太éĥİ
    -0.06
    éī
    -0.06
    -san
    -0.05
    è¼Ķ
    -0.05
     Interpret
    -0.05
    POSITIVE LOGITS
    Ñħи
    0.07
    Å¡ov
    0.07
     ragaz
    0.07
    bero
    0.07
     Allocator
    0.07
    isÃŃ
    0.06
    èĥİ
    0.06
    RefPtr
    0.06
    iston
    0.06
    ÑģÑıг
    0.06
    Activations Density 0.001%

    No Known Activations