© 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. 42296
    Prev
    Next
    INDEX
    Explanations

    references to jewelry and accessories

    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
    ackbar
    -0.08
    erli
    -0.07
    eer
    -0.07
    _ABI
    -0.06
    fee
    -0.06
    anvas
    -0.06
    cak
    -0.06
     drums
    -0.06
    irling
    -0.06
    ãģĭãĤĬ
    -0.06
    POSITIVE LOGITS
    eker
    0.07
    /button
    0.06
     button
    0.06
    PEND
    0.06
     cors
    0.06
    /Button
    0.06
     buttonText
    0.06
    -pin
    0.06
    Clip
    0.06
     undone
    0.06
    Activations Density 0.030%

    No Known Activations