© 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. 77261
    Prev
    Next
    INDEX
    Explanations

    financial metrics related to profit and loss

    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
    coni
    -0.07
    илÑı
    -0.07
    ovah
    -0.07
    atables
    -0.07
    ledon
    -0.06
    abaj
    -0.06
    mist
    -0.06
    .VideoCapture
    -0.06
    resh
    -0.06
     Weiner
    -0.06
    POSITIVE LOGITS
     lug
    0.07
    ĽĦ
    0.07
    owie
    0.07
     ken
    0.06
     Barcl
    0.06
     âĵĺ
    0.06
    iff
    0.06
    liÄį
    0.06
     pé
    0.06
    -score
    0.06
    Activations Density 0.000%

    No Known Activations