© 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. 127284
    Prev
    Next
    INDEX
    Explanations

    references to political figures and events

    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
    moth
    -0.09
    MemoryWarning
    -0.08
    .aspect
    -0.07
     ydk
    -0.07
     addCriterion
    -0.07
     migrationBuilder
    -0.07
    yd
    -0.07
    ãİ
    -0.07
    -cols
    -0.06
    ORMAT
    -0.06
    POSITIVE LOGITS
     visit
    0.09
     speech
    0.07
     personally
    0.07
    dio
    0.06
     word
    0.06
     address
    0.06
     visited
    0.06
     visiting
    0.06
     attend
    0.06
     meet
    0.06
    Activations Density 0.039%

    No Known Activations