Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4907
    Prev
    Next
    INDEX
    Explanations

    contexts related to the term "use" in technical and programming discussions

    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
     Všech
    -0.09
    .scalablytyped
    -0.08
    onet
    -0.08
    enders
    -0.08
    รà¸ĵ
    -0.08
    uren
    -0.07
     ëĦ¤ìĿ´íĬ¸
    -0.07
    @brief
    -0.07
    áºł
    -0.07
    á»ı
    -0.07
    POSITIVE LOGITS
     instead
    0.09
     either
    0.09
     only
    0.08
     exclusively
    0.07
     same
    0.07
     slightly
    0.06
     a
    0.06
     solely
    0.06
     the
    0.06
     separate
    0.06
    Activations Density 0.048%

    No Known Activations