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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76997
    Prev
    Next
    INDEX
    Explanations

    references to consumer protection and scams

    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
    .scalablytyped
    -0.10
     Raq
    -0.08
     fragmentation
    -0.06
     Ferrari
    -0.06
    ContentLoaded
    -0.06
     Fé
    -0.06
    .getChannel
    -0.06
     Emirates
    -0.06
     Columbia
    -0.06
    æĹıèĩªæ²»
    -0.06
    POSITIVE LOGITS
     Iowa
    0.21
     Moines
    0.14
     Sioux
    0.10
     Omaha
    0.10
    owa
    0.10
     Des
    0.09
    aukee
    0.09
     Waterloo
    0.09
     IA
    0.09
     Nebraska
    0.08
    Activations Density 0.095%

    No Known Activations