© 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. 87595
    Prev
    Next
    INDEX
    Explanations

    references to artillery and weaponry

    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
    åīij
    -0.07
    åĪĢ
    -0.06
     knife
    -0.06
    867
    -0.06
    flo
    -0.06
     sword
    -0.06
    enes
    -0.06
    rive
    -0.06
     swords
    -0.06
     knives
    -0.06
    POSITIVE LOGITS
    ä»°
    0.09
     firing
    0.09
     Fired
    0.09
    çŀ
    0.08
     feu
    0.08
    /goto
    0.07
     fired
    0.07
    ifax
    0.07
     íĻĶ
    0.07
     trang
    0.07
    Activations Density 0.029%

    No Known Activations