© 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. 9-LLAMASCOPE-RES-131K
    11. 96985
    Prev
    Next
    INDEX
    Explanations

    references to personal inboxes or mail

    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
     myself
    -0.07
    isor
    -0.07
    edo
    -0.06
    oom
    -0.06
    urb
    -0.06
     versions
    -0.06
    isos
    -0.06
     DataGridViewCellStyle
    -0.06
    zag
    -0.05
    ega
    -0.05
    POSITIVE LOGITS
     lÃłn
    0.07
    alary
    0.07
    566
    0.07
    ìĿ´ìŀIJ
    0.07
    ìĥģìĿĺ
    0.07
    ấy
    0.07
    ssi
    0.07
    ÙijÙĩ
    0.07
    SetFont
    0.07
     navegador
    0.07
    Activations Density 0.003%

    No Known Activations