© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28374
    Prev
    Next
    INDEX
    Explanations

    references to stylesheets and related web development elements

    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
    ONUS
    -0.06
     etc
    -0.06
    [
    -0.06
    asher
    -0.06
    ilon
    -0.06
     spo
    -0.06
     wast
    -0.06
    éo
    -0.06
    rips
    -0.06
    /Graphics
    -0.06
    POSITIVE LOGITS
    nofollow
    0.08
    ÑĤаж
    0.07
    ÏįÏĢ
    0.07
    ìĪł
    0.07
    å·»
    0.07
    =-=-
    0.07
    å±±å¸Ĥ
    0.07
     ÑģÑĩиÑĤа
    0.06
     ------------------------------------------------------------
    0.06
    CRT
    0.06
    Activations Density 0.001%

    No Known Activations