© 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. 128600
    Prev
    Next
    INDEX
    Explanations

    instances of communication and invitations to participate or collaborate

    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
     vent
    -0.06
    aldi
    -0.06
     dish
    -0.06
     memor
    -0.06
    ign
    -0.06
     social
    -0.06
    wen
    -0.06
    chalk
    -0.06
    ohn
    -0.06
    :convert
    -0.06
    POSITIVE LOGITS
    -send
    0.09
    ÏĨι
    0.08
    etler
    0.07
    Sending
    0.07
     Sending
    0.07
    sending
    0.07
    vala
    0.07
    ANTE
    0.07
     ë¶Ģíĥģ
    0.07
     Sends
    0.07
    Activations Density 0.024%

    No Known Activations