© 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. 77435
    Prev
    Next
    INDEX
    Explanations

    references to temptation and consumer urges

    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
    rame
    -0.07
    touches
    -0.06
    uliar
    -0.06
    izedName
    -0.06
    å§ĵ
    -0.06
    chestra
    -0.06
    veç
    -0.06
    TickCount
    -0.06
    asso
    -0.06
    ummer
    -0.06
    POSITIVE LOGITS
     temptation
    0.30
     tempting
    0.27
    tempt
    0.26
     tempt
    0.25
     tempted
    0.25
     sed
    0.17
     Tem
    0.17
     lure
    0.15
     Sed
    0.15
     enticing
    0.14
    Activations Density 0.111%

    No Known Activations