© 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. 56490
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the introduction of new laws or regulations

    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
    âĹİ
    -0.07
    ichert
    -0.07
    iedad
    -0.07
    æĺŃ
    -0.07
    ä¼´
    -0.07
    ucha
    -0.07
    imonial
    -0.07
    ething
    -0.06
     ç¯
    -0.06
    inear
    -0.06
    POSITIVE LOGITS
     publication
    0.07
     addition
    0.07
     introduction
    0.07
    åĬłåħ¥
    0.06
     posting
    0.06
     launch
    0.06
     passage
    0.06
     continued
    0.06
    ogan
    0.05
     added
    0.05
    Activations Density 0.029%

    No Known Activations