© 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. 107827
    Prev
    Next
    INDEX
    Explanations

    keywords and concepts related to software development and programming functions

    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
    .scalablytyped
    -0.09
    ÑĦоÑĢма
    -0.08
    -valu
    -0.08
     BITTE
    -0.07
    ê±°ëŀĺê°Ģ
    -0.07
    OffsetTable
    -0.07
    Intialized
    -0.07
    缸å½ĵ
    -0.07
    (coder
    -0.07
     UNICODE
    -0.07
    POSITIVE LOGITS
     non
    0.08
    non
    0.07
    uen
    0.07
    ynes
    0.07
    agas
    0.06
     Když
    0.06
    ign
    0.06
     cases
    0.06
    tech
    0.06
     stuff
    0.06
    Activations Density 0.046%

    No Known Activations