Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96227
    Prev
    Next
    INDEX
    Explanations

    visual indicators, such as colors and symbols, used to represent data in graphical formats

    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
     ÙĩÙħ
    -0.06
    ibold
    -0.06
    ingers
    -0.06
    zen
    -0.06
    652
    -0.06
    627
    -0.06
    utenberg
    -0.06
    781
    -0.06
    edin
    -0.06
    imus
    -0.06
    POSITIVE LOGITS
     McGr
    0.07
    oir
    0.06
    fait
    0.06
    obil
    0.06
     cánh
    0.06
     taped
    0.06
    ilib
    0.06
    metis
    0.06
     craw
    0.06
    hic
    0.06
    Activations Density 0.047%

    No Known Activations