© 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. 62413
    Prev
    Next
    INDEX
    Explanations

    repetitive or similar phrases in descriptions about things or concepts

    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
    /do
    -0.07
    หม
    -0.07
    ATRIX
    -0.07
    abajo
    -0.06
    Türkiye
    -0.06
     dzie
    -0.06
    lya
    -0.06
    trl
    -0.06
    ayscale
    -0.06
    کس
    -0.06
    POSITIVE LOGITS
     itself
    0.07
     novel
    0.07
    710
    0.07
    UAL
    0.06
     another
    0.06
    IVAL
    0.06
    gp
    0.06
     Carpenter
    0.06
     something
    0.06
    baum
    0.06
    Activations Density 0.041%

    No Known Activations