© 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. 55962
    Prev
    Next
    INDEX
    Explanations

    technical terms associated with audio mixing and signal processing

    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
    ä»ĵ
    -0.07
     atol
    -0.07
    nan
    -0.06
    inka
    -0.06
     IRA
    -0.06
    екÑĤÑĥ
    -0.06
    REATED
    -0.06
    sock
    -0.06
    .ud
    -0.06
     successor
    -0.06
    POSITIVE LOGITS
    kup
    0.07
    åĸ
    0.07
    Scaler
    0.07
    .inputs
    0.07
     heads
    0.06
    _puts
    0.06
    aisy
    0.06
     fed
    0.06
    FAULT
    0.06
     unity
    0.06
    Activations Density 0.079%

    No Known Activations