© 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. 73442
    Prev
    Next
    INDEX
    Explanations

    references to cryptocurrency and investment practices

    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
    imu
    -0.08
    rance
    -0.08
    arranty
    -0.07
    chwitz
    -0.07
    otron
    -0.07
    STA
    -0.07
    Commerce
    -0.07
    ãĥ©ãĥĥãĤ¯
    -0.07
    kees
    -0.07
    istrict
    -0.07
    POSITIVE LOGITS
     Dog
    0.07
     project
    0.07
     platform
    0.06
    validator
    0.06
     community
    0.06
     token
    0.06
     Token
    0.06
     capped
    0.06
    åħ
    0.06
     holders
    0.06
    Activations Density 0.012%

    No Known Activations