© 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. 126596
    Prev
    Next
    INDEX
    Explanations

    references to ivory and its uses or implications

    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
    alars
    -0.07
    elijk
    -0.07
    ropa
    -0.07
    nar
    -0.07
    ëĭ¤ëĬĶ
    -0.07
    nd
    -0.07
    uplic
    -0.07
    ĮĢ
    -0.07
    IPA
    -0.07
    ulled
    -0.06
    POSITIVE LOGITS
    smith
    0.07
    ede
    0.07
    ibs
    0.06
    omba
    0.06
    Äįer
    0.06
    geois
    0.06
    ony
    0.06
     Kra
    0.06
     tus
    0.06
    -white
    0.06
    Activations Density 0.001%

    No Known Activations