© 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. 81734
    Prev
    Next
    INDEX
    Explanations

    instances of overshadowing or being overshadowed in various contexts

    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
    ัà¸įà¸į
    -0.07
    æīĭãĤĴ
    -0.07
    å®Ī
    -0.06
    ystone
    -0.06
    uir
    -0.06
     pieces
    -0.06
    opr
    -0.06
    emi
    -0.06
    .cc
    -0.06
    ader
    -0.06
    POSITIVE LOGITS
     overshadow
    0.10
     eclips
    0.09
     shadow
    0.08
     eclipse
    0.08
     focus
    0.08
     competing
    0.08
    focus
    0.08
     usur
    0.08
    Focused
    0.07
    lij
    0.07
    Activations Density 0.047%

    No Known Activations