© 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. 69714
    Prev
    Next
    INDEX
    Explanations

    adjustments and modifications related to physical form and design

    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
     Pied
    -0.06
     birth
    -0.06
    sher
    -0.06
     nothing
    -0.06
    achen
    -0.06
    imu
    -0.06
    raki
    -0.06
     fur
    -0.06
    aeda
    -0.06
    @Spring
    -0.06
    POSITIVE LOGITS
     desired
    0.09
     adjust
    0.08
     adjustments
    0.08
     adjusting
    0.08
     Adjustment
    0.08
     adjustment
    0.08
     Adjust
    0.07
    ucas
    0.07
    Adjust
    0.07
    adjust
    0.07
    Activations Density 0.010%

    No Known Activations