© 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 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. 77209
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to mechanical or electrical systems

    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
     Raq
    -0.07
    ÑĢай
    -0.07
    éĢ¸
    -0.06
    PKG
    -0.06
     antennas
    -0.06
    lesai
    -0.06
    imli
    -0.06
    vir
    -0.06
    ovel
    -0.06
    geois
    -0.06
    POSITIVE LOGITS
    ำ
    0.07
     output
    0.06
    èĩ´
    0.06
    çĥŃ
    0.06
    OLF
    0.06
    _startup
    0.06
    sea
    0.06
    lea
    0.06
    uish
    0.06
    anders
    0.06
    Activations Density 0.016%

    No Known Activations