© 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. 94167
    Prev
    Next
    INDEX
    Explanations

    phrases associated with political actions or statements

    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
    ajes
    -0.07
    iscrim
    -0.06
    ısıt
    -0.06
    alous
    -0.06
    Popup
    -0.06
     naken
    -0.06
    ezier
    -0.06
    ìŀ¥ìĿ´
    -0.06
     ìĿ¸êµ¬
    -0.06
     Corey
    -0.06
    POSITIVE LOGITS
     himself
    0.07
     ticking
    0.07
    æī
    0.06
     yesterday
    0.06
     indirect
    0.06
    REATED
    0.06
     mic
    0.06
    [](
    0.06
    mlink
    0.06
     diplom
    0.06
    Activations Density 0.045%

    No Known Activations