© 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. 69752
    Prev
    Next
    INDEX
    Explanations

    references to the musical 'Les Misérables'

    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
    sf
    -0.06
    alic
    -0.06
     intrinsic
    -0.06
    lining
    -0.06
    annes
    -0.06
     rede
    -0.06
    ein
    -0.06
    .tt
    -0.05
    å¤ķ
    -0.05
     stdin
    -0.05
    POSITIVE LOGITS
    طاÙĤ
    0.07
    nar
    0.07
    AXB
    0.07
    PATCH
    0.07
    ány
    0.07
    jh
    0.07
    posables
    0.07
    patches
    0.07
    ModelProperty
    0.07
    encers
    0.06
    Activations Density 0.001%

    No Known Activations