© 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. 128957
    Prev
    Next
    INDEX
    Explanations

    details related to service offerings and assistance in specific locations

    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
    wer
    -0.05
     sever
    -0.05
     miss
    -0.05
     Sacred
    -0.05
    ooks
    -0.05
     Zimmerman
    -0.05
     Signed
    -0.05
    onu
    -0.05
     Iss
    -0.05
    ĺħ
    -0.05
    POSITIVE LOGITS
    еÑģÑĤи
    0.07
    cene
    0.07
    assa
    0.07
     ÙĨاب
    0.07
     kriz
    0.07
    arty
    0.07
    EventData
    0.07
    uvo
    0.07
    allet
    0.07
    olv
    0.07
    Activations Density 0.003%

    No Known Activations