© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 93856
    Prev
    Next
    INDEX
    Explanations

    specific geopolitical and social issues related to conflict and cultural topics

    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
    _REF
    -0.07
    iegel
    -0.07
     ans
    -0.06
    und
    -0.06
    ÄĻ
    -0.06
     Marvin
    -0.06
    .Experimental
    -0.06
    ỳ
    -0.06
     Seks
    -0.06
    ette
    -0.06
    POSITIVE LOGITS
     Uncategorized
    0.08
    #ad
    0.07
    enia
    0.07
    ãĤ¿ãĥ«
    0.07
    ););↵
    0.07
    WND
    0.07
    #ac
    0.06
    inded
    0.06
    chy
    0.06
    AccessType
    0.06
    Activations Density 0.057%

    No Known Activations