© 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. 92212
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to recognition and participation in award ceremonies or achievements

    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
    енка
    -0.08
     several
    -0.08
     же
    -0.07
    ãģŁãģı
    -0.07
    ëĬ
    -0.07
    ìĿ¸ìĿĺ
    -0.07
    WithMany
    -0.07
    enstein
    -0.07
    ISTER
    -0.07
    á»±
    -0.07
    POSITIVE LOGITS
     either
    0.17
     Either
    0.14
     EITHER
    0.13
    either
    0.12
     themselves
    0.12
    Either
    0.12
     varying
    0.09
     their
    0.09
     or
    0.09
     либо
    0.09
    Activations Density 0.076%

    No Known Activations