© 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. 92947
    Prev
    Next
    INDEX
    Explanations

    references to literature and literary topics

    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
    ey
    -0.08
    ements
    -0.07
    endas
    -0.07
    subtype
    -0.07
    ean
    -0.07
    ever
    -0.06
    onet
    -0.06
    uw
    -0.06
    TION
    -0.06
    گاÙĩ
    -0.06
    POSITIVE LOGITS
    urgical
    0.09
    atures
    0.08
    ally
    0.08
    atura
    0.07
    atur
    0.07
    ature
    0.07
     شع
    0.07
    زاÙħ
    0.06
    lle
    0.06
    hea
    0.06
    Activations Density 0.006%

    No Known Activations