© 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. 62032
    Prev
    Next
    INDEX
    Explanations

    phrases related to managing and reducing excess or burdens

    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
    isd
    -0.07
    bare
    -0.07
    sei
    -0.07
    NullException
    -0.07
    æ¢ģ
    -0.06
    /reference
    -0.06
    .setViewport
    -0.06
    ëĮĢë¡ľ
    -0.06
    abouts
    -0.06
    ACHI
    -0.06
    POSITIVE LOGITS
     old
    0.11
     excess
    0.10
     bad
    0.09
     unwanted
    0.09
     redundant
    0.08
    old
    0.08
    æŧ
    0.08
     obsolete
    0.08
    æİī
    0.08
     clutter
    0.07
    Activations Density 0.039%

    No Known Activations