© 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. 85790
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ownership or authorship in a scholarly context

    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
     hâl
    -0.07
    za
    -0.06
    ãĥģãĥ¥
    -0.06
    ograd
    -0.06
    زاÙħ
    -0.06
    hog
    -0.06
     denen
    -0.06
     beden
    -0.06
     Sant
    -0.06
     Wong
    -0.05
    POSITIVE LOGITS
     approach
    0.10
     Approach
    0.08
    appro
    0.07
    ftime
    0.07
    коÑĤ
    0.07
    _appro
    0.07
     results
    0.07
     findings
    0.07
    esy
    0.07
     APPRO
    0.07
    Activations Density 0.024%

    No Known Activations