© 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. 1796
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of "about."

    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
    lea
    -0.06
     Sle
    -0.06
     Ts
    -0.06
    riors
    -0.06
     fucks
    -0.05
     Wyn
    -0.05
    od
    -0.05
    ala
    -0.05
    orf
    -0.05
    atal
    -0.05
    POSITIVE LOGITS
    olian
    0.08
    gil
    0.07
    ê·¼
    0.07
    iaux
    0.07
     registrazione
    0.07
    630
    0.07
    elige
    0.07
    ched
    0.07
    avanaugh
    0.07
    ecko
    0.07
    Activations Density 0.005%

    No Known Activations