© 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. 117519
    Prev
    Next
    INDEX
    Explanations

    phrases related to memory and legacy

    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
    rai
    -0.07
    rescia
    -0.07
    akh
    -0.07
    amil
    -0.06
     panor
    -0.06
    ino
    -0.06
    exels
    -0.06
    nect
    -0.06
    kk
    -0.06
    ancies
    -0.06
    POSITIVE LOGITS
     legacy
    0.13
     Legacy
    0.11
    Legacy
    0.10
    legacy
    0.10
     leaving
    0.09
     Leave
    0.09
     mark
    0.09
     leave
    0.08
    leave
    0.08
     trace
    0.08
    Activations Density 0.013%

    No Known Activations