© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 26635
    Prev
    Next
    INDEX
    Explanations

    references to concepts of "frontiers" in various contexts

    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
    ãĥĨãĥ«
    -0.08
    avenport
    -0.08
    ularity
    -0.07
    erman
    -0.07
    heet
    -0.07
    /design
    -0.07
    ÏĥÏĢ
    -0.07
    olie
    -0.06
    оки
    -0.06
    keit
    -0.06
    POSITIVE LOGITS
    /back
    0.09
    /front
    0.09
    /ext
    0.07
    land
    0.07
     Carolyn
    0.07
    )((((
    0.07
    аÑĢÑĸ
    0.07
    ing
    0.06
    éĻħ
    0.06
    ously
    0.06
    Activations Density 0.006%

    No Known Activations