© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127995
    Prev
    Next
    INDEX
    Explanations

    titles or references to academic positions or titles

    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
     à¸ģรà¸ģ
    -0.07
    μÎŃ
    -0.07
    _USB
    -0.06
     appearances
    -0.06
    боÑĤ
    -0.06
    ALAR
    -0.06
    odash
    -0.06
    bidden
    -0.06
    awn
    -0.06
    ä¿Ĭ
    -0.06
    POSITIVE LOGITS
     lorem
    0.07
    por
    0.06
    vars
    0.06
    aeper
    0.06
    999
    0.06
     Graphic
    0.06
     McGu
    0.06
    071
    0.06
    -valu
    0.06
    bor
    0.06
    Activations Density 0.000%

    No Known Activations