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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14966
    Prev
    Next
    INDEX
    Explanations

    phrases related to complex problem-solving and investment strategies

    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
    anela
    -0.07
    -addons
    -0.07
    aminer
    -0.07
    инов
    -0.07
    resco
    -0.06
    agnar
    -0.06
    loff
    -0.06
    ét
    -0.06
     Rapids
    -0.06
     rap
    -0.06
    POSITIVE LOGITS
     preced
    0.10
     reverse
    0.09
    reverse
    0.09
     THEN
    0.09
     first
    0.09
    åħĪ
    0.09
    preced
    0.08
     preceded
    0.08
    Reverse
    0.08
     Reverse
    0.08
    Activations Density 0.037%

    No Known Activations