© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 128808
    Prev
    Next
    INDEX
    Explanations

    phrases indicating dedication or commitment to a specific purpose or goal

    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
    è«
    -0.07
    à¤ľà¤°
    -0.07
    eer
    -0.06
     meisten
    -0.06
    adora
    -0.06
    ernaut
    -0.06
    ingly
    -0.06
    imators
    -0.06
    nh
    -0.06
    ADOR
    -0.06
    POSITIVE LOGITS
    (FALSE
    0.07
    Äįet
    0.06
     ensuring
    0.06
     building
    0.06
     understanding
    0.06
    irsch
    0.06
    anco
    0.06
     causes
    0.06
    Slinky
    0.06
    recall
    0.06
    Activations Density 0.012%

    No Known Activations