© 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. 17400
    Prev
    Next
    INDEX
    Explanations

    references to spreadsheets and data management concepts

    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
     вд
    -0.07
    çĪ
    -0.07
    stad
    -0.06
    swire
    -0.06
    uted
    -0.06
     tu
    -0.06
    ledge
    -0.06
    linkplain
    -0.06
     dead
    -0.06
    ikut
    -0.06
    POSITIVE LOGITS
     Sheet
    0.08
    _sheet
    0.08
    pras
    0.08
     sheets
    0.07
    ë¸
    0.07
     sheet
    0.07
    named
    0.07
     named
    0.07
    (sheet
    0.07
     Sheets
    0.07
    Activations Density 0.001%

    No Known Activations