© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 76659
    Prev
    Next
    INDEX
    Explanations

    periods and formatting related to numerical information

    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
    icast
    -0.08
    ibold
    -0.08
    oodoo
    -0.07
    lide
    -0.07
     лиÑĪ
    -0.07
    rica
    -0.07
    ichen
    -0.07
    patrick
    -0.07
    forth
    -0.07
    regs
    -0.06
    POSITIVE LOGITS
     consider
    0.06
    nP
    0.06
    udo
    0.06
    994
    0.06
     Nass
    0.06
    ertain
    0.06
     advis
    0.06
    Sometimes
    0.05
    Ìģ
    0.05
    ounter
    0.05
    Activations Density 0.129%

    No Known Activations