© 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. 106922
    Prev
    Next
    INDEX
    Explanations

    information related to availability and accessibility of resources

    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
    oub
    -0.06
    OTE
    -0.06
    allon
    -0.06
    otec
    -0.06
    alte
    -0.06
    ade
    -0.06
    amt
    -0.05
    ãģ¾ãģ¨
    -0.05
     |_|
    -0.05
    idence
    -0.05
    POSITIVE LOGITS
     unlike
    0.40
     Unlike
    0.28
    Unlike
    0.28
     whereas
    0.25
     Whereas
    0.22
     compared
    0.20
     contrary
    0.17
     contrast
    0.15
     Compared
    0.15
     Contrast
    0.15
    Activations Density 0.112%

    No Known Activations