© 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. 127295
    Prev
    Next
    INDEX
    Explanations

    concepts and terms associated with minimalism

    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
    et
    -0.07
    iw
    -0.07
    liness
    -0.07
     dile
    -0.07
    eten
    -0.06
    ed
    -0.06
    ability
    -0.06
    e
    -0.06
    es
    -0.06
     Barg
    -0.06
    POSITIVE LOGITS
    istic
    0.13
    /max
    0.13
    ize
    0.11
    ogy
    0.11
    ized
    0.11
    izing
    0.11
    ists
    0.11
    izes
    0.10
    ization
    0.10
    ogue
    0.10
    Activations Density 0.009%

    No Known Activations