© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107154
    Prev
    Next
    INDEX
    Explanations

    occurrences of quotation marks and asynchronous JavaScript references

    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
     Floyd
    -0.07
     physical
    -0.07
    aines
    -0.06
     Yok
    -0.06
    ikipedia
    -0.06
    PDOException
    -0.06
    ubi
    -0.06
    heim
    -0.06
    rous
    -0.06
    inct
    -0.06
    POSITIVE LOGITS
    #ad
    0.08
    ãĥ³ãĤ¬
    0.07
    poll
    0.07
    /cgi
    0.06
     didFinish
    0.06
     Laden
    0.06
    Registered
    0.06
    owitz
    0.06
    tega
    0.06
    =$('#
    0.06
    Activations Density 0.005%

    No Known Activations