© 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. 5031
    Prev
    Next
    INDEX
    Explanations

    figures and graphical representations related to data in a scientific context

    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
    AFE
    -0.08
    имв
    -0.07
    ooter
    -0.07
    ôt
    -0.07
    atars
    -0.07
    akov
    -0.07
    inaire
    -0.07
    ptom
    -0.07
    Ãły
    -0.07
    ÙĪاÙĨ
    -0.07
    POSITIVE LOGITS
    âŁ
    0.06
    chod
    0.06
    andler
    0.06
    chy
    0.06
    n
    0.06
     stiff
    0.06
    iman
    0.06
    329
    0.06
     Surg
    0.05
    ider
    0.05
    Activations Density 0.025%

    No Known Activations