© 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. 17-LLAMASCOPE-RES-131K
    11. 128619
    Prev
    Next
    INDEX
    Explanations

    expressions related to opportunities and timing

    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
    anto
    -0.07
    ML
    -0.06
    ryn
    -0.06
     quota
    -0.06
    ofi
    -0.06
    ifact
    -0.06
     Pero
    -0.06
    lish
    -0.06
    mouseleave
    -0.06
    igos
    -0.06
    POSITIVE LOGITS
     iken
    0.08
    still
    0.08
     still
    0.07
    .metamodel
    0.07
    'gc
    0.07
    olut
    0.07
     còn
    0.07
    -fashion
    0.07
    recht
    0.07
    à¥įà¤Łà¤®
    0.07
    Activations Density 0.005%

    No Known Activations