© 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. 15-LLAMASCOPE-RES-131K
    11. 88589
    Prev
    Next
    INDEX
    Explanations

    phrases related to ratings and reviews of media

    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
    esi
    -0.06
     Gardner
    -0.06
     per
    -0.06
     Zd
    -0.06
    614
    -0.06
    atur
    -0.06
     Concepts
    -0.06
     Lowe
    -0.06
     Ap
    -0.05
    811
    -0.05
    POSITIVE LOGITS
    hausen
    0.08
    eyen
    0.07
    ibble
    0.07
    umer
    0.07
    Expires
    0.06
    erer
    0.06
    upe
    0.06
    /cop
    0.06
    ila
    0.06
    InChildren
    0.06
    Activations Density 0.003%

    No Known Activations