© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40144
    Prev
    Next
    INDEX
    Explanations

    expressions of recommendation or obligation

    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
     yine
    -0.07
    ijken
    -0.07
     <!--[
    -0.07
    onces
    -0.06
     گر
    -0.06
    urre
    -0.06
    anik
    -0.06
     تش
    -0.06
     Yine
    -0.06
    ire
    -0.06
    POSITIVE LOGITS
     every
    0.09
     perman
    0.07
     Every
    0.07
    every
    0.06
     everyone
    0.06
    Every
    0.06
     permanently
    0.06
    LookAndFeel
    0.06
     permanent
    0.06
     wider
    0.06
    Activations Density 0.023%

    No Known Activations