© 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. 61896
    Prev
    Next
    INDEX
    Explanations

    terms related to vaccinations and immunizations

    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
    avor
    -0.07
    TestCase
    -0.07
    asar
    -0.07
    acen
    -0.07
    inha
    -0.07
    anner
    -0.06
    íĴĪ
    -0.06
    alties
    -0.06
    enu
    -0.06
    Test
    -0.06
    POSITIVE LOGITS
    sWith
    0.06
    lico
    0.06
     Hav
    0.06
    485
    0.06
    -related
    0.06
    _coverage
    0.06
    roupon
    0.06
    taire
    0.06
    /MPL
    0.06
    rypton
    0.06
    Activations Density 0.008%

    No Known Activations