© 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. 61386
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs describing quantity, size, or severity

    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
    iska
    -0.08
    оÑĢод
    -0.08
    egen
    -0.07
    ekt
    -0.07
    keit
    -0.07
    zte
    -0.07
    ubern
    -0.07
    yonel
    -0.07
    ÃŃrk
    -0.07
    μον
    -0.07
    POSITIVE LOGITS
     that
    0.09
    that
    0.08
     bahwa
    0.07
     hogy
    0.06
     dass
    0.06
    auc
    0.06
     että
    0.06
    úa
    0.06
     Word
    0.06
    uts
    0.05
    Activations Density 0.028%

    No Known Activations