© 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. 76821
    Prev
    Next
    INDEX
    Explanations

    terms related to communication and its regulations

    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
    omo
    -0.08
    avou
    -0.07
    ноÑĩ
    -0.07
    ouser
    -0.06
    chio
    -0.06
    ipar
    -0.06
    æŃ©
    -0.06
     mug
    -0.06
    èŃ
    -0.06
    elters
    -0.06
    POSITIVE LOGITS
    ikit
    0.08
    statt
    0.07
    Recipient
    0.07
     Wiki
    0.07
     recipients
    0.07
     recipient
    0.06
     receivers
    0.06
    ãĤ«ãĥĨãĤ´ãĥª
    0.06
    Attachments
    0.06
    attachments
    0.06
    Activations Density 0.002%

    No Known Activations