© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103920
    Prev
    Next
    INDEX
    Explanations

    references to constraints within a programming context

    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
    WF
    -0.07
    .au
    -0.07
    scape
    -0.07
    sie
    -0.07
    еÑģÑĤв
    -0.07
    ATALOG
    -0.07
    czas
    -0.07
    teen
    -0.06
    ness
    -0.06
    éo
    -0.06
    POSITIVE LOGITS
    گر
    0.07
    inel
    0.07
    ional
    0.07
    pNet
    0.07
    orp
    0.07
    ioned
    0.06
    axed
    0.06
     Braz
    0.06
    edly
    0.06
    ala
    0.06
    Activations Density 0.028%

    No Known Activations