© 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. 88386
    Prev
    Next
    INDEX
    Explanations

    colons followed by numerical values or notes

    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
    yar
    -0.06
    zin
    -0.06
    мами
    -0.06
     then
    -0.06
    Ïĥμο
    -0.06
    ysa
    -0.06
     Böylece
    -0.06
    inte
    -0.06
    ëį°
    -0.06
    леÑĤ
    -0.06
    POSITIVE LOGITS
    untu
    0.07
    pill
    0.07
    -lnd
    0.07
    olla
    0.06
    URLException
    0.06
     There
    0.06
    afx
    0.06
    ceptar
    0.06
    enschaft
    0.06
    ackbar
    0.06
    Activations Density 0.013%

    No Known Activations