© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 38706
    Prev
    Next
    INDEX
    Explanations

    references to crusades and related historical themes

    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
    xit
    -0.07
    isz
    -0.07
    riv
    -0.06
    õ
    -0.06
    oon
    -0.06
    ality
    -0.06
    μÏĨ
    -0.06
    chen
    -0.06
     Leer
    -0.06
    onga
    -0.06
    POSITIVE LOGITS
    åĽ£
    0.07
    adol
    0.07
    popular
    0.07
    antine
    0.07
    à¸Ħร
    0.07
    raki
    0.07
    ByExample
    0.07
     popular
    0.07
    -era
    0.07
    òng
    0.07
    Activations Density 0.002%

    No Known Activations