© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61253
    Prev
    Next
    INDEX
    Explanations

    technical terms related to sound engineering 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
    reuse
    -0.08
    ungi
    -0.07
    uste
    -0.07
    bine
    -0.07
     reuse
    -0.06
     reused
    -0.06
     neglig
    -0.06
    _SCOPE
    -0.06
    รà¸Ķ
    -0.06
    ÏĦον
    -0.06
    POSITIVE LOGITS
     extra
    0.10
     compens
    0.08
     additional
    0.08
     Extra
    0.08
    extra
    0.08
     resort
    0.08
    Extra
    0.07
    .extra
    0.07
     designs
    0.07
     compensation
    0.07
    Activations Density 0.084%

    No Known Activations