© 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. 118564
    Prev
    Next
    INDEX
    Explanations

    parentheses and their contents in code snippets

    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
    iper
    -0.07
    406
    -0.07
    807
    -0.06
    unnel
    -0.06
    vey
    -0.06
     Dip
    -0.06
     dip
    -0.06
    ooth
    -0.06
    acks
    -0.06
    agas
    -0.06
    POSITIVE LOGITS
    ses
    0.09
     nonatomic
    0.08
    è¦ļ
    0.08
     Ãľst
    0.07
    ãĥ
    0.07
     Nack
    0.07
    lamaz
    0.07
    ENU
    0.07
    CHK
    0.07
    anne
    0.07
    Activations Density 0.002%

    No Known Activations