© 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. 15197
    Prev
    Next
    INDEX
    Explanations

    conjunctions that indicate comparison or similarity

    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
     ÑĢеб
    -0.07
    coe
    -0.07
    _decl
    -0.06
     yani
    -0.06
    AGMA
    -0.06
     thus
    -0.06
    .Ui
    -0.06
     indeed
    -0.06
    å´İ
    -0.06
    reon
    -0.06
    POSITIVE LOGITS
     ÙģØ¥ÙĨ
    0.07
    arily
    0.07
    andex
    0.07
    ersions
    0.07
    ily
    0.06
    mente
    0.06
     importantly
    0.06
    aneously
    0.06
     Ele
    0.06
    a
    0.06
    Activations Density 0.010%

    No Known Activations