© 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. 92299
    Prev
    Next
    INDEX
    Explanations

    references to quantities and the concept of inclusivity

    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
    fred
    -0.06
    ion
    -0.06
     for
    -0.06
    aro
    -0.06
    eno
    -0.06
    for
    -0.06
    ane
    -0.06
    onia
    -0.06
    imal
    -0.06
     Dexter
    -0.05
    POSITIVE LOGITS
     purposes
    0.10
     reasons
    0.10
    ges
    0.09
    aging
    0.09
    geries
    0.09
     instance
    0.08
     sake
    0.08
    ays
    0.08
     example
    0.08
    chten
    0.08
    Activations Density 0.058%

    No Known Activations