© 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. 104476
    Prev
    Next
    INDEX
    Explanations

    evaluative phrases regarding the quality and humor of books in a series

    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
     (
    -0.07
     we
    -0.06
     our
    -0.06
     :
    -0.06
    -0.06
     Or
    -0.06
    bote
    -0.06
    0
    -0.06
    ctor
    -0.06
     when
    -0.06
    POSITIVE LOGITS
     \"$
    0.08
    зн
    0.07
    usra
    0.07
     Å¡p
    0.07
     outr
    0.07
     AudioSource
    0.07
     ...)
    0.07
    Ïĩεία
    0.06
    azor
    0.06
    ILED
    0.06
    Activations Density 0.005%

    No Known Activations