© 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. 128605
    Prev
    Next
    INDEX
    Explanations

    programming elements related to software development and class definitions

    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
    773
    -0.06
    728
    -0.06
    SWG
    -0.06
    uby
    -0.06
     Lund
    -0.06
    .MSG
    -0.05
    mojom
    -0.05
     Reason
    -0.05
    urb
    -0.05
    erland
    -0.05
    POSITIVE LOGITS
    emente
    0.07
    éŀ
    0.07
    ehler
    0.06
    ilos
    0.06
    anter
    0.06
    ippi
    0.06
    iance
    0.06
    wend
    0.06
    ante
    0.06
     muž
    0.06
    Activations Density 0.005%

    No Known Activations