© 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. 15047
    Prev
    Next
    INDEX
    Explanations

    beliefs and assumptions expressed in the text

    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
    igin
    -0.07
    ort
    -0.07
    uzzi
    -0.06
    stadt
    -0.06
    ãĥ¼ãĥŃ
    -0.06
    rie
    -0.06
    Gam
    -0.06
    -state
    -0.06
    itarian
    -0.06
    res
    -0.06
    POSITIVE LOGITS
     only
    0.07
     Only
    0.07
     μÏĮνο
    0.07
    ONLY
    0.06
     synonym
    0.06
    koa
    0.06
     cứ
    0.06
    çµ
    0.06
     æ¶
    0.06
    .addHandler
    0.06
    Activations Density 0.018%

    No Known Activations