© 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. 105160
    Prev
    Next
    INDEX
    Explanations

    connecting phrases that signify comparison or contrast

    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
    ĶåĽŀ
    -0.07
     respectively
    -0.07
     Uncategorized
    -0.07
    tru
    -0.07
    adu
    -0.06
    дÑı
    -0.06
    Otherwise
    -0.06
    Coeff
    -0.06
     Fletcher
    -0.06
    jo
    -0.06
    POSITIVE LOGITS
     many
    0.10
     some
    0.10
     ones
    0.10
    some
    0.10
     each
    0.09
    many
    0.09
     meisten
    0.09
     Ones
    0.09
     ëĮĢë¶Ģë¶Ħ
    0.08
     mostly
    0.08
    Activations Density 0.063%

    No Known Activations