© 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 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. 88767
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations, particularly related to algorithms and functions

    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
    STANCE
    -0.07
    znám
    -0.07
    ĥĿ
    -0.07
    .opensource
    -0.07
     Nah
    -0.07
     pestic
    -0.06
    cka
    -0.06
    Ń
    -0.06
    ABCDEFGHI
    -0.06
    ød
    -0.06
    POSITIVE LOGITS
    2
    0.16
    Û²
    0.10
     Two
    0.09
    २
    0.09
    Ù¢
    0.09
    âĤĤ
    0.09
    äºĮ
    0.08
     II
    0.08
     Second
    0.08
    âij¡
    0.08
    Activations Density 0.235%

    No Known Activations