© 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. 14619
    Prev
    Next
    INDEX
    Explanations

    information related to space research initiatives

    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
    oba
    -0.07
    oling
    -0.06
    eced
    -0.06
    ecz
    -0.06
    allest
    -0.06
    еко
    -0.06
    chter
    -0.06
    ãİ
    -0.06
     dup
    -0.06
     variables
    -0.06
    POSITIVE LOGITS
     missions
    0.08
     Deep
    0.07
     deep
    0.07
    QUIRE
    0.07
    شتÙĩ
    0.06
    flater
    0.06
    {:
    0.06
     Headquarters
    0.06
    .fits
    0.06
    burst
    0.06
    Activations Density 0.007%

    No Known Activations