© 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 EvalsExportsAPI 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. 128890
    Prev
    Next
    INDEX
    Explanations

    references to the word "crystal" and its variations

    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
    es
    -0.07
    esin
    -0.07
    iaux
    -0.07
    imson
    -0.06
    Inspectable
    -0.06
    ximo
    -0.06
    eson
    -0.06
    ijo
    -0.06
    rowsable
    -0.06
    ãĥ³ãĤ°
    -0.06
    POSITIVE LOGITS
    -clear
    0.10
     clear
    0.09
    clear
    0.08
     Clear
    0.08
    CLEAR
    0.08
    .clear
    0.08
    log
    0.07
    ize
    0.07
    Clear
    0.07
    _clear
    0.07
    Activations Density 0.002%

    No Known Activations