© 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 EvalsExportsAPI 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. 71341
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and expressions of enthusiasm or appreciation

    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
    chg
    -0.07
    ozor
    -0.07
    ÑĥÑģÑĤа
    -0.07
    راÙĨÙĩ
    -0.06
    795
    -0.06
    á»Ļi
    -0.06
    ansk
    -0.06
    á»±a
    -0.06
    endar
    -0.06
    reau
    -0.06
    POSITIVE LOGITS
    elon
    0.08
     Sle
    0.07
    adeon
    0.06
    енÑĮ
    0.06
    -fw
    0.06
    /help
    0.06
     bunch
    0.06
    egas
    0.06
     ims
    0.06
     Hund
    0.06
    Activations Density 0.030%

    No Known Activations