© 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. 79907
    Prev
    Next
    INDEX
    Explanations

    descriptions of atmosphere and emotional states in a setting

    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
    olik
    -0.07
     integr
    -0.06
    emma
    -0.06
    oling
    -0.06
     genie
    -0.05
     modern
    -0.05
     \@
    -0.05
     Trib
    -0.05
     lab
    -0.05
     Ros
    -0.05
    POSITIVE LOGITS
     atmosphere
    0.15
     air
    0.14
    à¸Ńาà¸ģาศ
    0.12
    air
    0.10
     vzdu
    0.10
     atmos
    0.10
     воздÑĥÑħа
    0.10
    -air
    0.09
     Atmos
    0.09
     ambiente
    0.09
    Activations Density 0.061%

    No Known Activations