© 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. 73044
    Prev
    Next
    INDEX
    Explanations

    concepts and imagery related to the sky and celestial objects

    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
    545
    -0.06
    rien
    -0.06
     getattr
    -0.06
     Shapiro
    -0.06
     Crescent
    -0.06
    urs
    -0.06
     Sans
    -0.06
    ngine
    -0.06
    åħ³
    -0.06
    Aceptar
    -0.06
    POSITIVE LOGITS
     sky
    0.12
     Sky
    0.12
    Sky
    0.11
    /cloud
    0.10
     skies
    0.09
    sky
    0.09
     ceiling
    0.08
     Cloud
    0.08
    Cloud
    0.08
    cloud
    0.08
    Activations Density 0.005%

    No Known Activations