© 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. 126229
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical notation and graph theory

    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
    obo
    -0.06
     prompt
    -0.06
    ä¸ĬäºĨ
    -0.06
     Yüz
    -0.06
    ovsky
    -0.06
    èĪį
    -0.06
    presso
    -0.06
     HÃłnh
    -0.06
     accessible
    -0.05
    ThanOrEqualTo
    -0.05
    POSITIVE LOGITS
    ourcem
    0.08
    abil
    0.08
    oire
    0.06
    orpor
    0.06
    jedn
    0.06
    zes
    0.06
    -INFRINGEMENT
    0.06
    Ïĥή
    0.06
    ulin
    0.06
     '&'
    0.06
    Activations Density 0.173%

    No Known Activations