© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 105779
    Prev
    Next
    INDEX
    Explanations

    technical terms related to processing and transmitting digital signals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Technical terms or variable names within programming code, database fields, or specifications, often representing parameters, measurements, or identifiers in JSON, SQL, or other technical contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    OfSize
    -0.06
    ýš
    -0.06
    ëĬ¥
    -0.06
    deÅŁ
    -0.06
    kili
    -0.06
    Âł
    -0.06
    _COMPAT
    -0.06
     addCriterion
    -0.06
    ebek
    -0.05
    ideographic
    -0.05
    POSITIVE LOGITS
     ðŁĺī↵↵
    0.07
     ÑĦедеÑĢалÑĮ
    0.07
    anging
    0.07
    ystate
    0.07
    acimiento
    0.07
    .mvc
    0.07
     pÅĻiÄįemž
    0.07
     ðŁĻĤ↵↵
    0.07
    .MixedReality
    0.06
    ÑĢовиÑĩ
    0.06
    Activations Density 3.608%

    No Known Activations