© 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. 17791
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and concepts related to fractions

    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
    [OF
    -0.06
    918
    -0.06
    360
    -0.06
    locals
    -0.06
    rollers
    -0.06
    ephy
    -0.06
     Prospect
    -0.06
    420
    -0.06
    lane
    -0.06
    edBy
    -0.06
    POSITIVE LOGITS
    pes
    0.07
    quat
    0.07
    mixed
    0.06
    zac
    0.06
    AXB
    0.06
     situations
    0.06
    axon
    0.06
     involves
    0.06
    ÏĦικ
    0.06
     involving
    0.06
    Activations Density 0.004%

    No Known Activations