© 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. 56025
    Prev
    Next
    INDEX
    Explanations

    financial performance indicators related to a company's stock

    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
    xmm
    -0.07
    ossier
    -0.07
     Fuji
    -0.06
    etsk
    -0.06
    legg
    -0.06
     Lazar
    -0.06
    essa
    -0.06
    isclosed
    -0.06
    iaux
    -0.06
    enton
    -0.06
    POSITIVE LOGITS
    upert
    0.07
    usch
    0.07
    TestCategory
    0.07
     Turtle
    0.06
    èĮ
    0.06
    fade
    0.06
    ngo
    0.06
    lyph
    0.06
    JsonValue
    0.06
    ContentView
    0.06
    Activations Density 0.004%

    No Known Activations