© 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. 56077
    Prev
    Next
    INDEX
    Explanations

    phrases indicating financial transactions or agreements

    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
    acher
    -0.07
    .scalablytyped
    -0.07
    Ðĭ
    -0.07
    @nate
    -0.07
    ibal
    -0.07
    Occurred
    -0.07
     ÑĥÑħ
    -0.06
    ichel
    -0.06
     Tire
    -0.06
    ften
    -0.06
    POSITIVE LOGITS
    sey
    0.07
    wa
    0.06
     Roths
    0.06
    wu
    0.06
     stuff
    0.06
     sæ
    0.06
     cider
    0.06
    Stuff
    0.06
    uddle
    0.06
    .opendaylight
    0.06
    Activations Density 0.001%

    No Known Activations