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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16837
    Prev
    Next
    INDEX
    Explanations

    technical terms related to speaker design and acoustic properties

    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
    ollar
    -0.07
     Enterprise
    -0.07
     abst
    -0.07
    ennes
    -0.06
    hip
    -0.06
    åħIJ
    -0.06
    ãĥ³ãĥ
    -0.06
     im
    -0.06
     Alman
    -0.06
    StateManager
    -0.06
    POSITIVE LOGITS
     speaker
    0.09
     loud
    0.08
     Speakers
    0.08
     speakers
    0.08
    peaker
    0.07
    Speaker
    0.07
     reproduce
    0.07
     reproduced
    0.07
     ac
    0.07
     bass
    0.07
    Activations Density 0.146%

    No Known Activations