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

    Neuronpedia

    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. 87040
    Prev
    Next
    INDEX
    Explanations

    references to people involved in political activities or 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
    оÑģÑĥд
    -0.09
    Та
    -0.09
    ¶Į
    -0.08
    еÑĢÑĪ
    -0.08
    _________________↵↵
    -0.08
     fitte
    -0.08
     mrt
    -0.08
    connexion
    -0.08
    .Toolkit
    -0.07
    .Formatter
    -0.07
    POSITIVE LOGITS
     Uncategorized
    0.11
    by
    0.06
    anner
    0.06
     via
    0.06
    plat
    0.06
    0.06
    ancy
    0.06
    ith
    0.05
    atri
    0.05
    amo
    0.05
    Activations Density 0.005%

    No Known Activations