© 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. 42182
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases related to comparisons or contrasts

    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
    achuset
    -0.08
    GenerationStrategy
    -0.07
    SGlobal
    -0.06
    )((((
    -0.06
    販
    -0.06
     ClassName
    -0.06
     ÂŃ
    -0.06
    úsqueda
    -0.06
    /Core
    -0.06
    lier
    -0.05
    POSITIVE LOGITS
    oret
    0.10
    bsite
    0.09
    oretical
    0.08
    ept
    0.08
    dit
    0.07
     responseObject
    0.07
    ALES
    0.07
    ksam
    0.07
    åŃĹ
    0.07
    onds
    0.07
    Activations Density 0.072%

    No Known Activations