© 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 EvalsExportsinterp-engineNEWAPI 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. 17425
    Prev
    Next
    INDEX
    Explanations

    phrases indicating change and adaptation

    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
    zung
    -0.09
    nero
    -0.07
    urances
    -0.06
    indr
    -0.06
     Boss
    -0.06
    upo
    -0.06
    arded
    -0.06
    lettes
    -0.06
     biomedical
    -0.06
    ounded
    -0.06
    POSITIVE LOGITS
    owitz
    0.06
    Ïģαβ
    0.06
    cript
    0.06
    affe
    0.06
     WHATSOEVER
    0.06
    ern
    0.06
    UnitTest
    0.06
     Nass
    0.06
    ÑĤеÑĢн
    0.06
    Clip
    0.06
    Activations Density 0.002%

    No Known Activations