© 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. 93326
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to economics and philosophical ideas

    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
    lett
    -0.08
    eyed
    -0.06
    frey
    -0.06
    letal
    -0.06
    strar
    -0.06
    itant
    -0.06
    tails
    -0.06
    INESS
    -0.06
    thin
    -0.06
     Chan
    -0.06
    POSITIVE LOGITS
    ically
    0.10
    ally
    0.08
    ums
    0.07
    als
    0.07
    umblr
    0.07
    ino
    0.07
    ate
    0.07
    etri
    0.07
    ics
    0.07
    ria
    0.07
    Activations Density 0.113%

    No Known Activations