© 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. 28947
    Prev
    Next
    INDEX
    Explanations

    references to specifications and attributes related to objects or entities

    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
    oload
    -0.10
    ofilm
    -0.09
    ityEngine
    -0.08
    ynet
    -0.08
    ¼åIJĪ
    -0.08
    ă
    -0.08
    FileSync
    -0.07
     OnTrigger
    -0.07
    èIJ
    -0.07
    inyin
    -0.07
    POSITIVE LOGITS
     The
    0.07
     âĢ¢
    0.07
     Figure
    0.07
    0.06
     I
    0.06
    âĢIJ
    0.06
     D
    0.06
     Gray
    0.06
     Mull
    0.06
     For
    0.06
    Activations Density 0.001%

    No Known Activations