© 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. 81302
    Prev
    Next
    INDEX
    Explanations

    instances of the word "remember" and its variations, indicating a focus on recollection and memory

    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
    avanaugh
    -0.07
    obus
    -0.07
    sei
    -0.07
    eteria
    -0.07
    EVENT
    -0.06
    ei
    -0.06
    adolu
    -0.06
    loven
    -0.06
    akat
    -0.06
    owers
    -0.06
    POSITIVE LOGITS
     when
    0.10
     similar
    0.08
     similarly
    0.08
    when
    0.07
     years
    0.07
     cuando
    0.07
    entimes
    0.07
    unken
    0.07
     childhood
    0.07
     conversations
    0.07
    Activations Density 0.011%

    No Known Activations