© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 125432
    Prev
    Next
    INDEX
    Explanations

    references to music or sound, particularly related to tunes

    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
    enso
    -0.07
     Wohnung
    -0.06
     Shepard
    -0.06
    /goto
    -0.06
    ristol
    -0.06
    ence
    -0.06
    ождениÑı
    -0.06
    ivec
    -0.06
    ÙĪجÙĩ
    -0.06
     teardown
    -0.06
    POSITIVE LOGITS
    arily
    0.07
    tras
    0.06
    ãĤĤãģ®
    0.06
    TEGER
    0.06
     clin
    0.06
    vise
    0.06
     proton
    0.06
    ecz
    0.06
    lies
    0.06
    gba
    0.06
    Activations Density 0.001%

    No Known Activations