© 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. 17-LLAMASCOPE-RES-131K
    11. 15884
    Prev
    Next
    INDEX
    Explanations

    references to libraries and standards

    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
     ring
    -0.06
    ymoon
    -0.06
    ivic
    -0.06
    ury
    -0.06
    ercul
    -0.06
    è¨
    -0.06
     kul
    -0.06
     nues
    -0.06
     zd
    -0.05
    chte
    -0.05
    POSITIVE LOGITS
    å¼¥
    0.07
     addslashes
    0.06
    ysz
    0.06
     GiỼi
    0.06
    itat
    0.06
    inality
    0.06
    udd
    0.06
    luk
    0.06
    CTYPE
    0.06
    UNT
    0.06
    Activations Density 0.000%

    No Known Activations