© 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. 118509
    Prev
    Next
    INDEX
    Explanations

    references to consent for receiving marketing communications

    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
    asion
    -0.07
    oi
    -0.06
     stab
    -0.06
     vak
    -0.06
     spre
    -0.06
    .ERR
    -0.06
     Consulting
    -0.06
    ilton
    -0.06
    tees
    -0.06
    ove
    -0.06
    POSITIVE LOGITS
     Wig
    0.07
    -aut
    0.07
    using
    0.07
    okt
    0.07
    \CMS
    0.06
     Amp
    0.06
    eza
    0.06
    aut
    0.06
    ittel
    0.06
     ÄĮesko
    0.06
    Activations Density 0.006%

    No Known Activations