© 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. 84564
    Prev
    Next
    INDEX
    Explanations

    terms related to legislative actions and removal processes

    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
    ä¸į好
    -0.07
    845
    -0.07
    acey
    -0.06
    reme
    -0.06
    اÙĤ
    -0.06
     queryInterface
    -0.06
    560
    -0.06
     Tune
    -0.06
    wd
    -0.06
    strap
    -0.06
    POSITIVE LOGITS
    abox
    0.08
    iasi
    0.07
     barriers
    0.07
    /change
    0.07
    ">ÃĹ</
    0.07
     ÐľÐ¸
    0.07
    ibase
    0.07
    ë¡ľëĤĺ
    0.06
     Ded
    0.06
    /remove
    0.06
    Activations Density 0.019%

    No Known Activations