© 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. 57009
    Prev
    Next
    INDEX
    Explanations

    variations of the word "congratulations."

    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
    quin
    -0.07
    iera
    -0.07
    æĤł
    -0.07
    icable
    -0.06
    ÑģÑĤика
    -0.06
    _SOCKET
    -0.06
    ific
    -0.06
    uga
    -0.06
    indre
    -0.06
    brands
    -0.06
    POSITIVE LOGITS
    estion
    0.08
    446
    0.07
     Cong
    0.07
    ault
    0.07
    Cong
    0.07
    445
    0.07
    rats
    0.07
    ÏĥÏĦαν
    0.07
     Lik
    0.07
    regation
    0.06
    Activations Density 0.008%

    No Known Activations