© 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. 42370
    Prev
    Next
    INDEX
    Explanations

    references to Karl Marx and his theories

    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
    ioctl
    -0.07
    xic
    -0.06
    lass
    -0.06
    gest
    -0.06
    erness
    -0.06
    gether
    -0.06
    lisi
    -0.06
     independence
    -0.06
    xford
    -0.06
    onor
    -0.06
    POSITIVE LOGITS
    -len
    0.08
    tober
    0.08
    enstein
    0.08
     Overs
    0.07
    ists
    0.07
    ipel
    0.07
    itten
    0.07
    ÛĮاÙĨ
    0.07
    ismu
    0.07
    Ñģли
    0.06
    Activations Density 0.003%

    No Known Activations