© 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 EvalsExportsAPI 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. 3470
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and data management

    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
    opsis
    -0.07
    raya
    -0.07
    ikh
    -0.06
    Ãłng
    -0.06
    ienes
    -0.06
    Ìģt
    -0.06
    ikip
    -0.06
    ekler
    -0.06
    adder
    -0.06
    Ậ
    -0.06
    POSITIVE LOGITS
    nels
    0.06
    æĮģ
    0.06
    .addHandler
    0.06
     Woj
    0.06
    all
    0.06
    ochen
    0.06
    uous
    0.06
    ηÏĤ
    0.06
    .enterprise
    0.06
    ernaut
    0.06
    Activations Density 0.072%

    No Known Activations