© 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. 1994
    Prev
    Next
    INDEX
    Explanations

    terms and information related to visa applications and processes

    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
    Release
    -0.07
     releases
    -0.06
    zap
    -0.06
     Release
    -0.06
     Cannon
    -0.06
    ardon
    -0.06
    itivity
    -0.06
     Wort
    -0.06
    _hdl
    -0.06
    .opensource
    -0.06
    POSITIVE LOGITS
     visa
    0.07
    ayo
    0.07
     overst
    0.06
     колÑĮ
    0.06
     Gro
    0.06
    üven
    0.06
     FindObjectOfType
    0.06
    vre
    0.06
    BED
    0.06
    anik
    0.06
    Activations Density 0.016%

    No Known Activations