© 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. 9-LLAMASCOPE-RES-131K
    11. 98820
    Prev
    Next
    INDEX
    Explanations

    elements of a narrative involving people in challenging situations

    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
    astle
    -0.06
    angent
    -0.06
    rale
    -0.06
    mlin
    -0.06
    зв
    -0.06
    ninger
    -0.06
    pare
    -0.06
    qq
    -0.06
    ippi
    -0.06
    rell
    -0.06
    POSITIVE LOGITS
    >window
    0.07
    elu
    0.06
    uns
    0.06
     samot
    0.06
    å¾ģ
    0.06
     traditionally
    0.06
    Schedulers
    0.06
    kar
    0.06
     Wright
    0.06
    iggs
    0.06
    Activations Density 0.020%

    No Known Activations