© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 130144
    Prev
    Next
    INDEX
    Explanations

    statements about existence or identity

    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
    ide
    -0.08
    onga
    -0.07
    ishly
    -0.07
    unsch
    -0.07
    jon
    -0.07
    cio
    -0.06
    isman
    -0.06
    aurus
    -0.06
    ÑĢеÑī
    -0.06
    ÄĻ
    -0.06
    POSITIVE LOGITS
     why
    0.09
    why
    0.07
    bast
    0.07
     Bast
    0.07
    ãĤ¸ãĤ¢
    0.07
    enger
    0.07
     Ziel
    0.06
     INCIDENT
    0.06
     Ledger
    0.06
    Calibri
    0.06
    Activations Density 0.018%

    No Known Activations