© 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. 93797
    Prev
    Next
    INDEX
    Explanations

    references to political and social influence related to governmental processes and actions

    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
    _________________↵↵
    -0.11
    .DropDown
    -0.11
    maktan
    -0.09
    /******/
    -0.09
    _CNTL
    -0.09
     Pazar
    -0.09
    ÙĬÙĦاد
    -0.09
     Böl
    -0.09
    ¿ÃĤ
    -0.09
    ÏģοÏį
    -0.09
    POSITIVE LOGITS
    âĢ¦↵
    0.09
    <|end_of_text|>
    0.07
    ab
    0.07
    ci
    0.07
    ...↵
    0.07
    iro
    0.07
    0.07
    Âł
    0.06
    ast
    0.06
     famously
    0.06
    Activations Density 0.180%

    No Known Activations