© 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. 17-LLAMASCOPE-RES-131K
    11. 95038
    Prev
    Next
    INDEX
    Explanations

    metrics related to computer resource usage during attacks

    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
    пÑĢиклад
    -0.07
    anse
    -0.07
    ÃŃst
    -0.07
     Stout
    -0.07
    enor
    -0.06
     floppy
    -0.06
    ç¥Ń
    -0.06
    eldo
    -0.06
    ffe
    -0.06
    ubbo
    -0.06
    POSITIVE LOGITS
     Bethesda
    0.06
     sustained
    0.06
    erra
    0.06
    çĽij
    0.06
     steady
    0.06
    CPP
    0.06
    licher
    0.06
    indr
    0.06
    afari
    0.06
    ائÙħ
    0.06
    Activations Density 0.010%

    No Known Activations