© 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. 90155
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exceptions or exclusions

    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
    pte
    -0.07
    ahr
    -0.07
    acement
    -0.07
    heimer
    -0.07
    ÃŃc
    -0.07
    ito
    -0.07
    hea
    -0.06
    icts
    -0.06
    enna
    -0.06
    ÏĢλα
    -0.06
    POSITIVE LOGITS
    Та
    0.06
     unless
    0.06
    unless
    0.06
    Unless
    0.06
     Unless
    0.06
     intro
    0.06
    æķ¬
    0.06
    ersist
    0.05
    lectron
    0.05
     certain
    0.05
    Activations Density 0.019%

    No Known Activations