© 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. 124927
    Prev
    Next
    INDEX
    Explanations

    negative connotations associated with various topics

    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
    è·Ŀ
    -0.07
    оÑģÑĢед
    -0.07
    ibase
    -0.07
    åijĢ
    -0.06
     =(
    -0.06
    aphore
    -0.06
    δεÏĤ
    -0.06
     dek
    -0.06
    à¥įà¤
    -0.06
     spir
    -0.06
    POSITIVE LOGITS
    @dynamic
    0.07
    @nate
    0.07
    olan
    0.07
     Fay
    0.06
    ırak
    0.06
    ipp
    0.06
    urs
    0.06
    ills
    0.06
    /facebook
    0.06
    %C
    0.06
    Activations Density 0.021%

    No Known Activations