© 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. 15-LLAMASCOPE-RES-131K
    11. 104184
    Prev
    Next
    INDEX
    Explanations

    activities related to teaching and mentorship

    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
    assel
    -0.07
    åģ¥
    -0.07
    IDES
    -0.07
    slu
    -0.06
    ufen
    -0.06
    izon
    -0.06
    ิà¹Ģว
    -0.06
     Dear
    -0.06
    usted
    -0.06
    cum
    -0.06
    POSITIVE LOGITS
     others
    0.16
    others
    0.13
     other
    0.13
     Others
    0.11
    Others
    0.11
    other
    0.10
     altri
    0.10
     anderen
    0.10
     fellow
    0.09
     åħ¶ä»ĸ
    0.09
    Activations Density 0.029%

    No Known Activations