© 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. 93621
    Prev
    Next
    INDEX
    Explanations

    terms related to deterrence and the concept of preventing actions or behaviors

    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
    otted
    -0.07
    ilver
    -0.07
    ORIZONTAL
    -0.07
    elf
    -0.07
    /download
    -0.07
    رÛĮاÙĨ
    -0.06
    alsa
    -0.06
    rav
    -0.06
    onte
    -0.06
    ninger
    -0.06
    POSITIVE LOGITS
    upt
    0.08
     others
    0.07
    warts
    0.07
    rence
    0.07
    ingly
    0.07
    /mit
    0.07
    ERA
    0.07
     further
    0.07
     future
    0.07
    future
    0.06
    Activations Density 0.006%

    No Known Activations