© 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. 15-LLAMASCOPE-RES-131K
    11. 90174
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage in the context of text

    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
    EMA
    -0.07
    thouse
    -0.07
    ldkf
    -0.06
    781
    -0.06
    iah
    -0.06
    ISTA
    -0.06
    636
    -0.06
    anian
    -0.06
    erne
    -0.06
    anning
    -0.06
    POSITIVE LOGITS
    elines
    0.07
    abet
    0.06
     AIDS
    0.06
    aira
    0.06
    ises
    0.06
    &&(
    0.06
     Barber
    0.05
     bare
    0.05
    asurable
    0.05
     confront
    0.05
    Activations Density 0.001%

    No Known Activations