© 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. 16070
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to convolutional neural networks

    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
    bud
    -0.07
    jsx
    -0.07
    lico
    -0.07
    ä¹İ
    -0.07
    iane
    -0.07
    æī
    -0.07
    ooter
    -0.06
    isplay
    -0.06
    bjerg
    -0.06
     *)((
    -0.06
    POSITIVE LOGITS
     stride
    0.07
     Tal
    0.07
     Sed
    0.06
    otel
    0.06
    ning
    0.06
    sole
    0.06
     covering
    0.06
     Morr
    0.06
     conv
    0.06
    XC
    0.06
    Activations Density 0.006%

    No Known Activations