© 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. 82901
    Prev
    Next
    INDEX
    Explanations

    references to casualties or loss of life

    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
    ÏĥÏĦα
    -0.07
    ãģ¥
    -0.07
    imli
    -0.07
     armed
    -0.07
    igham
    -0.07
    ierz
    -0.07
    mam
    -0.07
    ãĥ³ãĥĦ
    -0.07
     Sachs
    -0.07
    æ¨
    -0.07
    POSITIVE LOGITS
     losses
    0.10
     loss
    0.09
    loss
    0.09
     Loss
    0.08
    Loss
    0.07
     toll
    0.07
    Cas
    0.07
    cas
    0.07
     attr
    0.07
     injury
    0.06
    Activations Density 0.052%

    No Known Activations