© 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. 62396
    Prev
    Next
    INDEX
    Explanations

    specific names of albums and songs

    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
    CurrentValue
    -0.06
    esan
    -0.06
    INO
    -0.06
    ÑģÑı
    -0.06
    ony
    -0.06
     erw
    -0.06
     Tüm
    -0.06
    ListNode
    -0.06
    994
    -0.06
    icus
    -0.06
    POSITIVE LOGITS
     EP
    0.10
    EP
    0.08
    _EP
    0.07
     Sessions
    0.07
    zo
    0.07
    oba
    0.07
    Sessions
    0.07
     æ¥Ń
    0.06
    Zip
    0.06
    ailable
    0.06
    Activations Density 0.043%

    No Known Activations