© 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. 30627
    Prev
    Next
    INDEX
    Explanations

    actions related to management and operational tasks

    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
    ä½Ļ
    -0.08
     amd
    -0.08
    avis
    -0.08
    ozor
    -0.07
     и
    -0.07
    ses
    -0.07
    AndPassword
    -0.07
    енÑĮ
    -0.07
    ãģ¨
    -0.07
    ãĥ¼ãĥ
    -0.07
    POSITIVE LOGITS
     alike
    0.08
     them
    0.06
    atas
    0.06
    erve
    0.06
     eh
    0.06
    oldem
    0.06
     Fav
    0.06
    ardless
    0.05
    ause
    0.05
    ansa
    0.05
    Activations Density 0.014%

    No Known Activations