© 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. 92471
    Prev
    Next
    INDEX
    Explanations

    phrases related to the central importance or critical points within various contexts

    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
    Latch
    -0.07
    usan
    -0.07
    sez
    -0.07
    ahlen
    -0.07
    wyn
    -0.06
    uset
    -0.06
    еÑĢп
    -0.06
     sokak
    -0.06
    kud
    -0.06
    åİ
    -0.06
    POSITIVE LOGITS
     core
    0.15
     heart
    0.13
    core
    0.13
    -core
    0.11
    heart
    0.11
    /Core
    0.11
    -heart
    0.11
     pulse
    0.10
    (core
    0.10
     heartbeat
    0.10
    Activations Density 0.059%

    No Known Activations