© 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. 125085
    Prev
    Next
    INDEX
    Explanations

    expressions involving the concept of "with."

    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
    жно
    -0.07
    iete
    -0.07
    ucc
    -0.06
    wen
    -0.06
    ãİ
    -0.06
    Reusable
    -0.06
    OKIE
    -0.06
    \Resources
    -0.06
    .GetItem
    -0.06
    ÙĬØ«
    -0.06
    POSITIVE LOGITS
     other
    0.21
     others
    0.17
    other
    0.16
    åħ¶ä»ĸ
    0.14
     another
    0.14
    others
    0.13
     otras
    0.13
     altre
    0.13
     nhau
    0.13
     Other
    0.12
    Activations Density 0.070%

    No Known Activations