© 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. 78333
    Prev
    Next
    INDEX
    Explanations

    financial metrics and statistics related to business and investment

    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
    каÑģ
    -0.07
     воÑĤ
    -0.07
    ाà¤Ĺत
    -0.07
    ToObject
    -0.07
    Bu
    -0.07
    .UIManager
    -0.07
    è¾ĥ
    -0.07
     bu
    -0.07
    ãĥĨãĥ«
    -0.07
    ODEV
    -0.06
    POSITIVE LOGITS
     estimated
    0.09
     far
    0.08
     estimates
    0.07
     rival
    0.07
     tens
    0.07
     estimate
    0.07
    far
    0.06
    lak
    0.06
     over
    0.06
     world
    0.06
    Activations Density 0.030%

    No Known Activations