© 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. 9-LLAMASCOPE-RES-131K
    11. 94759
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical expressions

    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
    teen
    -0.08
    teenth
    -0.08
    iy
    -0.08
    -0.08
    bet
    -0.08
    ately
    -0.07
    chan
    -0.07
    nal
    -0.07
    PLE
    -0.07
    yun
    -0.07
    POSITIVE LOGITS
    ey
    0.09
    alen
    0.08
    alysis
    0.08
    istrovstvÃŃ
    0.08
    adera
    0.07
    redients
    0.07
    à¸ľ
    0.07
    aroo
    0.07
    ãģĬãĤĬ
    0.07
    bsite
    0.07
    Activations Density 0.362%

    No Known Activations