© 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. 120871
    Prev
    Next
    INDEX
    Explanations

    references to empirical data or proof within the text

    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
    isi
    -0.09
    side
    -0.08
    sWith
    -0.08
    /ros
    -0.07
    achten
    -0.07
    igel
    -0.07
    isma
    -0.07
    å¨ĺ
    -0.07
    Balancer
    -0.07
    خاÙĨÙĩ
    -0.07
    POSITIVE LOGITS
    lessly
    0.10
     Bob
    0.07
    uality
    0.07
    igner
    0.07
    abase
    0.07
    424
    0.06
    Bob
    0.06
    partials
    0.06
    ritt
    0.06
    iveness
    0.06
    Activations Density 0.013%

    No Known Activations