© 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. 78785
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their contextual significance

    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
    ÛĮرÙĩ
    -0.06
    ouden
    -0.06
     Yesterday
    -0.06
    all
    -0.06
    vet
    -0.06
     Osw
    -0.06
    undra
    -0.06
     Sadd
    -0.06
    ucc
    -0.06
     tomorrow
    -0.05
    POSITIVE LOGITS
     Worth
    0.08
    ÙĤÙħ
    0.08
     worth
    0.07
    worth
    0.07
    gaard
    0.07
     visit
    0.07
    æŁ¥çľĭ
    0.06
    ãĥ¬ãĥ³
    0.06
     originally
    0.06
    appointment
    0.06
    Activations Density 0.022%

    No Known Activations