© 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. 3690
    Prev
    Next
    INDEX
    Explanations

    terms related to oppression and systemic issues

    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
    rido
    -0.08
    icari
    -0.08
    _Insert
    -0.08
    оÑĢоÑĤ
    -0.07
     eskort
    -0.07
    neider
    -0.07
    .DOM
    -0.07
    aze
    -0.07
    اصÙĦÙĩ
    -0.07
    nect
    -0.07
    POSITIVE LOGITS
     somehow
    0.10
     or
    0.06
    ÂĿ
    0.06
    776
    0.06
     blah
    0.06
     Thur
    0.06
    |array
    0.05
    <|end_of_text|>
    0.05
     unw
    0.05
    ip
    0.05
    Activations Density 0.083%

    No Known Activations