Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82883
    Prev
    Next
    INDEX
    Explanations

    phrases related to announcements or formal declarations

    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
     zig
    -0.06
     touch
    -0.06
     Raq
    -0.06
     TOUCH
    -0.06
    gon
    -0.06
    olumn
    -0.06
     touching
    -0.05
    èľ
    -0.05
     mon
    -0.05
    852
    -0.05
    POSITIVE LOGITS
     hereby
    0.11
     announces
    0.11
     annonce
    0.11
     announce
    0.11
     annonces
    0.10
     Announcement
    0.09
     announcing
    0.09
    announce
    0.08
     Proud
    0.08
     annon
    0.08
    Activations Density 0.059%

    No Known Activations