© 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. 93250
    Prev
    Next
    INDEX
    Explanations

    references to directional movements and wind patterns

    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
    ourg
    -0.07
    istrat
    -0.07
    367
    -0.06
    969
    -0.06
    AttributeValue
    -0.06
    268
    -0.06
    -REAL
    -0.06
    uls
    -0.06
    umbledore
    -0.06
    olum
    -0.06
    POSITIVE LOGITS
    ward
    0.08
    internet
    0.08
     direction
    0.08
    æĸ¹åIJij
    0.08
    /left
    0.08
    wards
    0.07
    /down
    0.07
    _SHIFT
    0.07
     Wich
    0.07
    à¹Ģà¸ī
    0.07
    Activations Density 0.004%

    No Known Activations