© 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. 5-LLAMASCOPE-RES-131K
    11. 126788
    Prev
    Next
    INDEX
    Explanations

    uncommon or unique identifiers, particularly in names and locations

    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
    loud
    -0.08
    erve
    -0.07
    oz
    -0.07
    isper
    -0.07
    ois
    -0.07
     Dreams
    -0.07
    wins
    -0.07
    lings
    -0.06
    oj
    -0.06
    ope
    -0.06
    POSITIVE LOGITS
    swers
    0.07
    vyk
    0.07
    äºİ
    0.06
    surf
    0.06
    tics
    0.06
    azi
    0.06
    sert
    0.06
    olon
    0.06
    ennie
    0.06
    acerb
    0.06
    Activations Density 0.118%

    No Known Activations