© 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. 73615
    Prev
    Next
    INDEX
    Explanations

    statements critiquing political behavior and tactics

    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
    ibbon
    -0.08
    üçük
    -0.07
    indered
    -0.07
    983
    -0.07
     سÙĦاÙħ
    -0.07
    .mac
    -0.07
     аÑģп
    -0.07
    ίοÏĤ
    -0.07
    owy
    -0.07
    ughs
    -0.07
    POSITIVE LOGITS
     desperation
    0.09
     desperate
    0.08
     desper
    0.08
     attempt
    0.07
     unable
    0.07
     panic
    0.07
     inability
    0.07
     try
    0.07
     Cannot
    0.07
    .try
    0.07
    Activations Density 0.047%

    No Known Activations