© 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. 70118
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate curiosity or a suggestion of further exploration

    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
    ipa
    -0.07
    ç´ł
    -0.07
    azzi
    -0.07
    arte
    -0.06
    IPA
    -0.05
    az
    -0.05
    za
    -0.05
     Ingredient
    -0.05
    019
    -0.05
     ingredient
    -0.05
    POSITIVE LOGITS
    uguay
    0.07
    buster
    0.07
    strcasecmp
    0.07
    iras
    0.07
    'order
    0.07
     sami
    0.07
    ocate
    0.07
    EDIA
    0.07
     canh
    0.07
     efekt
    0.07
    Activations Density 0.000%

    No Known Activations