© 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. 92877
    Prev
    Next
    INDEX
    Explanations

    symbols and numbers used in mathematical or statistical contexts

    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
    hev
    -0.06
    oca
    -0.06
    onic
    -0.06
     screenWidth
    -0.06
    575
    -0.06
    aval
    -0.06
    DH
    -0.05
    achi
    -0.05
     Fore
    -0.05
     at
    -0.05
    POSITIVE LOGITS
     kou
    0.07
     Ipsum
    0.07
     YYSTYPE
    0.07
    çĽĺ
    0.07
    spd
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
     sıras
    0.06
    æĪ¸
    0.06
    inos
    0.06
    ,↵↵↵↵
    0.06
    Activations Density 0.001%

    No Known Activations