© 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. 39910
    Prev
    Next
    INDEX
    Explanations

    phrases indicating membership or association with groups or organizations

    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
    aland
    -0.09
     èı²å¾ĭ宾
    -0.08
    los
    -0.08
    Ïģιά
    -0.08
    ittal
    -0.07
    _ng
    -0.07
    ä¸įçŁ¥
    -0.07
     Ïį
    -0.07
    eland
    -0.07
     бог
    -0.07
    POSITIVE LOGITS
    elves
    0.06
     Congress
    0.06
    aight
    0.06
    caled
    0.06
    576
    0.06
     (
    0.06
     staff
    0.06
     starter
    0.05
     families
    0.05
     communities
    0.05
    Activations Density 0.011%

    No Known Activations