© 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. 15-LLAMASCOPE-RES-131K
    11. 90210
    Prev
    Next
    INDEX
    Explanations

    instances of quantification or measurement

    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
    ÑĤÑİ
    -0.07
    ifar
    -0.06
    ral
    -0.06
    omain
    -0.06
    ÑĦа
    -0.06
     trá»Ŀi
    -0.06
    rak
    -0.06
    brig
    -0.06
     spin
    -0.06
     continua
    -0.05
    POSITIVE LOGITS
    erture
    0.07
    andbox
    0.07
    JI
    0.07
    Bubble
    0.07
    ji
    0.06
    ë§ī
    0.06
    bubble
    0.06
    jis
    0.06
     overall
    0.06
    çIJ
    0.06
    Activations Density 0.029%

    No Known Activations