© 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. 17966
    Prev
    Next
    INDEX
    Explanations

    references to pets and petroleum-related topics

    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
    edList
    -0.08
    nave
    -0.07
    lander
    -0.07
     Ferry
    -0.07
    rnek
    -0.07
    gne
    -0.07
    lys
    -0.07
    ephir
    -0.06
    ignon
    -0.06
    ¾
    -0.06
    POSITIVE LOGITS
    ters
    0.11
    ted
    0.10
    ting
    0.09
    abytes
    0.08
    roleum
    0.07
    ten
    0.07
    apixel
    0.07
    abyte
    0.07
    unj
    0.07
    to
    0.07
    Activations Density 0.021%

    No Known Activations