© 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. 87648
    Prev
    Next
    INDEX
    Explanations

    words related to support for or opposition against specific political stances or movements

    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
    rof
    -0.07
    ro
    -0.07
    wap
    -0.07
     ÎłÏģÏī
    -0.06
    -elected
    -0.06
    xiety
    -0.06
    755
    -0.06
    á»Ļi
    -0.06
    uju
    -0.06
    enegro
    -0.06
    POSITIVE LOGITS
    ably
    0.07
    ffer
    0.07
     pro
    0.07
    bst
    0.07
    tracted
    0.07
    logue
    0.06
    pped
    0.06
    esses
    0.06
    actively
    0.06
    ANO
    0.06
    Activations Density 0.014%

    No Known Activations