© 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. 84653
    Prev
    Next
    INDEX
    Explanations

    references to price thresholds or alerts related to promotions

    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
    interopRequire
    -0.07
    rowsing
    -0.07
    &&!
    -0.06
    kar
    -0.06
    AH
    -0.06
    bic
    -0.06
     mic
    -0.06
    i
    -0.06
    Å¡e
    -0.06
    óng
    -0.05
    POSITIVE LOGITS
    aisy
    0.07
    ambi
    0.07
     hers
    0.07
    izza
    0.07
    ÃĹ↵↵
    0.07
    aes
    0.07
    123
    0.06
     Widget
    0.06
    ulls
    0.06
    åıİ
    0.06
    Activations Density 0.000%

    No Known Activations