© 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. 60578
    Prev
    Next
    INDEX
    Explanations

    phrases that express a relationship or contrast between different ideas or elements

    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
     sez
    -0.07
    koli
    -0.07
    üyle
    -0.06
    ãĥŃãĥ³
    -0.06
    mlink
    -0.06
    gom
    -0.06
    .generated
    -0.06
    ÌĨ
    -0.06
    allo
    -0.06
    },'
    -0.06
    POSITIVE LOGITS
     etc
    0.14
    etc
    0.11
    çŃī
    0.07
    ozÃŃ
    0.06
    ENCHMARK
    0.06
    Lastly
    0.06
     ect
    0.06
    /etc
    0.06
     basically
    0.06
    ãģªãģ©
    0.06
    Activations Density 0.141%

    No Known Activations