© 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. 84125
    Prev
    Next
    INDEX
    Explanations

    information related to political activism and persecution

    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
     absentee
    -0.07
    ether
    -0.07
     mdl
    -0.06
    èĤ
    -0.06
     Marin
    -0.06
    ocal
    -0.06
    رÙĬÙģ
    -0.06
     اÙĦخاÙħسة
    -0.06
     uranus
    -0.06
     fashionable
    -0.06
    POSITIVE LOGITS
    izr
    0.08
    passport
    0.08
     flight
    0.07
     sanctuary
    0.07
     passport
    0.07
    yonel
    0.07
     escape
    0.07
     legal
    0.07
    ucher
    0.07
     ref
    0.06
    Activations Density 0.017%

    No Known Activations