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

    Neuronpedia

    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. 83713
    Prev
    Next
    INDEX
    Explanations

    mentions of "poly," indicating a focus on materials or compounds related to polymers

    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
    irk
    -0.07
    pill
    -0.07
    lund
    -0.07
    NESS
    -0.07
    ald
    -0.06
    la
    -0.06
    le
    -0.06
    ness
    -0.06
    uala
    -0.06
    æ´ĭ
    -0.06
    POSITIVE LOGITS
    gons
    0.10
    lien
    0.07
    heimer
    0.07
    meric
    0.07
    loff
    0.07
    oment
    0.07
     préc
    0.07
    álo
    0.07
    ethylene
    0.07
    orphic
    0.07
    Activations Density 0.006%

    No Known Activations