© 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 EvalsExportsinterp-engineNEWAPI 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. 17664
    Prev
    Next
    INDEX
    Explanations

    the word "as" in various contexts and frequencies

    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
    å¥Ĺ
    -0.07
    757
    -0.07
    æµľ
    -0.07
    ay
    -0.06
    oÄį
    -0.06
    aps
    -0.06
    essler
    -0.06
     Buckley
    -0.06
    ach
    -0.06
    èµĦæł¼
    -0.06
    POSITIVE LOGITS
    anker
    0.07
    loyd
    0.07
     Tone
    0.06
    395
    0.06
    ãĤ¸
    0.06
    Tek
    0.06
    ÑĢÑİ
    0.06
    à¥ģह
    0.06
    setFlash
    0.06
    bat
    0.06
    Activations Density 0.001%

    No Known Activations