© 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 EvalsExportsAPI 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. 78556
    Prev
    Next
    INDEX
    Explanations

    phrases related to musical production and experiences

    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
    ilight
    -0.07
    azon
    -0.07
    resh
    -0.07
     movies
    -0.07
    _cores
    -0.06
     æĺ
    -0.06
    AssignableFrom
    -0.06
    assi
    -0.06
     kijken
    -0.06
     calculus
    -0.06
    POSITIVE LOGITS
     studio
    0.13
     sessions
    0.11
     recording
    0.10
     session
    0.10
    studio
    0.10
     Studio
    0.09
     Recording
    0.09
    Studio
    0.09
    -session
    0.08
     Session
    0.08
    Activations Density 0.067%

    No Known Activations