© 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. 92934
    Prev
    Next
    INDEX
    Explanations

    references to age and the identity of individuals

    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
    imar
    -0.07
    angkan
    -0.07
    .ie
    -0.07
    ös
    -0.07
    ioni
    -0.07
    zc
    -0.06
    ÏĥÏĦε
    -0.06
    Ø®ÛĮ
    -0.06
     mktime
    -0.06
     Lanka
    -0.06
    POSITIVE LOGITS
     hometown
    0.10
     native
    0.10
     located
    0.09
    located
    0.08
     domic
    0.08
     headquartered
    0.08
     Located
    0.08
     اÙĩÙĦ
    0.08
    .native
    0.07
    native
    0.07
    Activations Density 0.073%

    No Known Activations