© 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. 61805
    Prev
    Next
    INDEX
    Explanations

    mentions of products and services, especially in a commercial 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
    ided
    -0.07
    áÄį
    -0.07
    orns
    -0.07
    iá»ĥm
    -0.07
     Dou
    -0.07
    arge
    -0.07
    ",__
    -0.06
    Digits
    -0.06
    aised
    -0.06
    rell
    -0.06
    POSITIVE LOGITS
    æ£
    0.07
    erdem
    0.06
    uria
    0.06
    uzzi
    0.06
    bjerg
    0.06
    cej
    0.06
    hof
    0.06
    nej
    0.06
    .atom
    0.06
    пон
    0.06
    Activations Density 0.250%

    No Known Activations