© 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 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. 125729
    Prev
    Next
    INDEX
    Explanations

    references to financial and personal struggles

    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
    živ
    -0.08
    ån
    -0.08
    iếu
    -0.08
    ccione
    -0.08
    uilder
    -0.08
    oler
    -0.08
    leck
    -0.08
    anou
    -0.07
    onga
    -0.07
    à¥ĩशà¤ķ
    -0.07
    POSITIVE LOGITS
     of
    0.09
     của
    0.08
     those
    0.07
    à¹īาà¸Ĥà¸Ńà¸ĩ
    0.06
     certain
    0.06
     ÏĦÏīν
    0.06
     backs
    0.06
     od
    0.05
    mf
    0.05
     each
    0.05
    Activations Density 0.072%

    No Known Activations