© 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. 59328
    Prev
    Next
    INDEX
    Explanations

    mentions of political actions and interactions among various officials and governments

    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
    longleftrightarrow
    -0.08
    opens
    -0.07
    ımızın
    -0.06
    translator
    -0.06
    ibold
    -0.06
     tang
    -0.06
    _INCREMENT
    -0.06
     ceremon
    -0.06
    iard
    -0.06
     ceremonial
    -0.06
    POSITIVE LOGITS
     sources
    0.10
     Sources
    0.09
    Sources
    0.08
     Src
    0.08
     insiders
    0.08
     src
    0.07
    sources
    0.07
    Priv
    0.07
     internal
    0.07
     Dün
    0.07
    Activations Density 0.073%

    No Known Activations