© 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. 62182
    Prev
    Next
    INDEX
    Explanations

    terms related to age groups and restrictions

    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
    724
    -0.06
     Geç
    -0.06
    ÑĢап
    -0.05
    267
    -0.05
    agas
    -0.05
    yro
    -0.05
    aan
    -0.05
    Disallow
    -0.05
     hed
    -0.05
    469
    -0.05
    POSITIVE LOGITS
     ÛĮعÙĨÛĮ
    0.14
     yani
    0.14
     ÑĤобÑĤо
    0.09
     defined
    0.09
     tức
    0.09
    defined
    0.09
    ï¼Įåį³
    0.09
     ie
    0.08
     (
    0.08
     (\<
    0.08
    Activations Density 0.130%

    No Known Activations