© 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. 9-LLAMASCOPE-RES-131K
    11. 98380
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of smoothness or fluidity

    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
    áct
    -0.07
    ngr
    -0.07
    kir
    -0.07
    />\
    -0.07
    imson
    -0.07
    .gdx
    -0.07
    abet
    -0.07
    htub
    -0.07
    apia
    -0.06
    htar
    -0.06
    POSITIVE LOGITS
    ness
    0.08
    íķĻê³¼
    0.08
    ly
    0.08
    posium
    0.07
    ily
    0.07
    ening
    0.07
    ier
    0.07
    ely
    0.07
    -flow
    0.07
     viá»ĩc
    0.07
    Activations Density 0.011%

    No Known Activations