© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56579
    Prev
    Next
    INDEX
    Explanations

    details about team performance and individual player contributions

    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
    LBL
    -0.08
    exus
    -0.08
    ationship
    -0.07
     겨
    -0.07
    alach
    -0.07
     Danh
    -0.07
    éļĨ
    -0.07
    .slim
    -0.07
    رÛĮÙģ
    -0.07
    æ³ķ人
    -0.06
    POSITIVE LOGITS
     contributions
    0.07
     
    0.07
     two
    0.06
     contribution
    0.06
     Arbitrary
    0.06
     ability
    0.06
    rogen
    0.06
    rom
    0.06
    Pager
    0.06
    _rng
    0.06
    Activations Density 0.019%

    No Known Activations