© 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 EvalsExportsAPI 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. 128601
    Prev
    Next
    INDEX
    Explanations

    references to supernatural phenomena and personal experiences with the paranormal

    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
    /ajax
    -0.06
    ch
    -0.06
     catapult
    -0.06
    ¹
    -0.06
    kid
    -0.05
    chos
    -0.05
     too
    -0.05
     profit
    -0.05
     traction
    -0.05
     splash
    -0.05
    POSITIVE LOGITS
    ãĥ³ãĤ°ãĥ«
    0.09
    enty
    0.08
     sond
    0.07
    ysi
    0.07
     Boutique
    0.07
    peria
    0.07
    omanip
    0.07
    berra
    0.07
     Weinstein
    0.07
    gars
    0.07
    Activations Density 0.001%

    No Known Activations