© 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. 4629
    Prev
    Next
    INDEX
    Explanations

    themes related to environmental sustainability and innovative technologies

    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
    [,]
    -0.07
    andre
    -0.07
     préc
    -0.07
     muh
    -0.07
    æīįèĥ½
    -0.07
    abwe
    -0.07
    اعÙĬ
    -0.06
     architekt
    -0.06
    ahren
    -0.06
     célib
    -0.06
    POSITIVE LOGITS
     recently
    0.10
    recent
    0.08
     recent
    0.08
    Recently
    0.07
     another
    0.07
     very
    0.07
     lately
    0.07
    osto
    0.07
    again
    0.06
     Recently
    0.06
    Activations Density 0.035%

    No Known Activations