© 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. 54999
    Prev
    Next
    INDEX
    Explanations

    references to EPs (extended plays) and LPs (long plays) in music contexts

    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
     tarafından
    -0.07
    IME
    -0.07
    254
    -0.06
    .dispatcher
    -0.06
     Oscars
    -0.06
    balls
    -0.06
    afa
    -0.06
    ysz
    -0.06
    eled
    -0.06
    /sys
    -0.06
    POSITIVE LOGITS
    -length
    0.09
    -release
    0.08
    RELEASE
    0.08
    ISODE
    0.07
    -sized
    0.07
    važ
    0.07
    -range
    0.07
     release
    0.07
    sik
    0.07
    release
    0.07
    Activations Density 0.004%

    No Known Activations