© 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. 117355
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics, particularly related to employment and economic metrics

    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
    relay
    -0.08
    dealloc
    -0.07
    lobals
    -0.07
    ivil
    -0.07
    mobx
    -0.07
    tero
    -0.07
    ุล
    -0.07
    å°ĸ
    -0.07
    toi
    -0.06
    ghi
    -0.06
    POSITIVE LOGITS
     to
    0.08
     earlier
    0.07
    adle
    0.06
     originally
    0.06
    лек
    0.06
    ãĢįãĤĴ
    0.06
     into
    0.06
     Ø¥ÙĦÙī
    0.06
    rib
    0.06
    piar
    0.06
    Activations Density 0.011%

    No Known Activations