© 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. 93102
    Prev
    Next
    INDEX
    Explanations

    issues related to environmental sustainability and ethical practices in industries

    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
     SPDX
    -0.06
    ium
    -0.06
    itel
    -0.06
    ringe
    -0.06
    leyen
    -0.06
     maxLength
    -0.06
    rup
    -0.06
    μάÏĦÏīν
    -0.06
    ryn
    -0.06
    »¿
    -0.06
    POSITIVE LOGITS
     statistics
    0.18
     Statistics
    0.18
     stats
    0.15
    Statistics
    0.15
     statistic
    0.15
    statistics
    0.15
    Stats
    0.14
     Stats
    0.14
    stats
    0.13
    -stats
    0.13
    Activations Density 0.356%

    No Known Activations