© 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. 17850
    Prev
    Next
    INDEX
    Explanations

    technical terms and abbreviations related to technology and communication protocols

    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
    Å¡ti
    -0.07
    /people
    -0.06
    ãĥĨãĥ«
    -0.06
    Ú©ÛĮÙĦ
    -0.06
    rames
    -0.06
    Å¡tÃŃ
    -0.06
    people
    -0.06
    /-
    -0.06
    ãĤĽ
    -0.06
     Bacon
    -0.06
    POSITIVE LOGITS
    inode
    0.07
    inity
    0.07
    arel
    0.07
    atron
    0.06
    .ejb
    0.06
    merce
    0.06
    etta
    0.06
    LATED
    0.06
    (gca
    0.06
     molec
    0.06
    Activations Density 0.029%

    No Known Activations