© 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. 75411
    Prev
    Next
    INDEX
    Explanations

    references to well-known album titles and artists

    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
     solo
    -0.06
     alone
    -0.06
     Bris
    -0.06
    zym
    -0.05
     пÑĢид
    -0.05
     ex
    -0.05
     dello
    -0.05
    963
    -0.05
    uida
    -0.05
     hy
    -0.05
    POSITIVE LOGITS
     ActionTypes
    0.09
     kino
    0.08
    å·
    0.08
     BTN
    0.07
     زاد
    0.07
     mastur
    0.07
     Blow
    0.07
    esub
    0.07
    ãĥ³ãĤº
    0.07
     Whe
    0.07
    Activations Density 0.047%

    No Known Activations