© 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. 56397
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters in the 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
    erte
    -0.07
    Ñİ
    -0.07
    berg
    -0.07
    оÐ
    -0.06
    ù
    -0.06
    ">//
    -0.06
     Bosch
    -0.06
     ÑĨÑĸй
    -0.06
    ness
    -0.06
     consc
    -0.06
    POSITIVE LOGITS
    ucer
    0.07
    ithe
    0.07
     name
    0.06
    okud
    0.06
    inders
    0.06
    asca
    0.06
     content
    0.06
    azon
    0.06
    arine
    0.06
    aná
    0.06
    Activations Density 0.084%

    No Known Activations