© 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. 17-LLAMASCOPE-RES-131K
    11. 127936
    Prev
    Next
    INDEX
    Explanations

    financial figures and economic data

    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
    urdy
    -0.07
    cheiden
    -0.06
    /thumb
    -0.06
    ROP
    -0.06
     ÎłÎ±Î½
    -0.06
    %(
    -0.06
    avin
    -0.06
    411
    -0.06
    ãĥĥãĥĦ
    -0.06
    ypass
    -0.06
    POSITIVE LOGITS
    FINE
    0.07
    Schedulers
    0.07
    ovic
    0.06
    fet
    0.06
    estre
    0.06
    722
    0.06
    lesi
    0.06
    HCI
    0.06
    IRR
    0.06
     us
    0.06
    Activations Density 0.003%

    No Known Activations