© 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. 83825
    Prev
    Next
    INDEX
    Explanations

    concepts related to political ideologies and their critiques

    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
    .XR
    -0.08
    aset
    -0.08
     заклад
    -0.08
    egend
    -0.08
    azu
    -0.08
    attern
    -0.07
    .TabControl
    -0.07
    dech
    -0.07
    empo
    -0.07
    izedName
    -0.07
    POSITIVE LOGITS
     variants
    0.07
     Ident
    0.06
     fatal
    0.06
     left
    0.06
     (
    0.06
     anti
    0.06
     ultra
    0.06
     pure
    0.06
    ulp
    0.06
     non
    0.06
    Activations Density 0.096%

    No Known Activations