© 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. 80142
    Prev
    Next
    INDEX
    Explanations

    words related to music and performance

    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
    ypse
    -0.06
    entric
    -0.06
    liable
    -0.06
    ansas
    -0.06
    pants
    -0.06
    anine
    -0.06
    ite
    -0.06
    iac
    -0.06
    IZER
    -0.06
    pdata
    -0.06
    POSITIVE LOGITS
     Jam
    0.10
    Jam
    0.10
     jam
    0.09
    sterdam
    0.08
     jams
    0.08
    ison
    0.07
    -packed
    0.07
    worthy
    0.07
    jam
    0.07
    ISON
    0.07
    Activations Density 0.018%

    No Known Activations