© 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. 17622
    Prev
    Next
    INDEX
    Explanations

    references to camera specifications and ISO ratings

    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
    egend
    -0.07
    åIJĽ
    -0.07
    боÑĤ
    -0.06
    iez
    -0.06
     tavs
    -0.06
    iad
    -0.06
    ombo
    -0.06
    resse
    -0.06
     secular
    -0.06
    /embed
    -0.06
    POSITIVE LOGITS
     exposures
    0.09
     noise
    0.08
     Exposure
    0.08
     night
    0.08
     Noise
    0.08
    noise
    0.07
    Noise
    0.07
    steller
    0.07
     exposure
    0.07
    Ãłm
    0.07
    Activations Density 0.008%

    No Known Activations