© 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. 125190
    Prev
    Next
    INDEX
    Explanations

    terms related to internships and training programs

    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
    /or
    -0.08
    iginal
    -0.07
    561
    -0.07
     existing
    -0.06
     or
    -0.06
    ekk
    -0.06
    nth
    -0.06
    ÑĢави
    -0.06
    uida
    -0.06
     ret
    -0.06
    POSITIVE LOGITS
    ees
    0.08
    ÙĬج
    0.07
    %)↵↵
    0.07
     ↵↵
    0.07
    ¦¬
    0.07
    warts
    0.07
    _drvdata
    0.07
     tiá»ĥu
    0.07
    ACKET
    0.07
     =č↵
    0.07
    Activations Density 0.070%

    No Known Activations