© 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. 108327
    Prev
    Next
    INDEX
    Explanations

    scientific references to changes in the Earth's atmosphere and geological history

    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
     male
    -0.07
    erties
    -0.06
     motor
    -0.06
     Protective
    -0.06
     powder
    -0.06
    emento
    -0.06
     protective
    -0.06
     potent
    -0.06
    amps
    -0.06
    RICS
    -0.05
    POSITIVE LOGITS
    PACE
    0.08
    otope
    0.08
     Paleo
    0.07
    rlen
    0.07
     carbon
    0.07
     Carbon
    0.07
     FIXED
    0.07
    ÑĮко
    0.07
    dfa
    0.07
    Carbon
    0.07
    Activations Density 0.004%

    No Known Activations