© 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. 93122
    Prev
    Next
    INDEX
    Explanations

    concepts related to quantum physics research

    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
    ERO
    -0.08
    /REC
    -0.07
    nullable
    -0.07
    ÙħØŃ
    -0.06
     noqa
    -0.06
    assin
    -0.06
    vang
    -0.06
    argin
    -0.06
    ecom
    -0.06
    åŁĭ
    -0.06
    POSITIVE LOGITS
     trap
    0.07
     traps
    0.07
     trapped
    0.07
     Stam
    0.07
    _trap
    0.07
    oven
    0.07
     Rarity
    0.06
     fi
    0.06
    ispecies
    0.06
    iena
    0.06
    Activations Density 0.152%

    No Known Activations