© 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. 94767
    Prev
    Next
    INDEX
    Explanations

    quantities and ratings associated with various entities

    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
    lest
    -0.06
    sonian
    -0.06
    ener
    -0.06
    tons
    -0.06
    inci
    -0.06
    stown
    -0.06
    rous
    -0.06
    )prepare
    -0.06
    åĽŀ
    -0.05
     ilma
    -0.05
    POSITIVE LOGITS
    ayout
    0.07
    Slf
    0.07
    loat
    0.06
    ì¦Ī
    0.06
    ê°Ŀ
    0.06
     Gerard
    0.06
    assi
    0.06
    oader
    0.06
     Tail
    0.06
     Vys
    0.06
    Activations Density 0.001%

    No Known Activations