© 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. 38751
    Prev
    Next
    INDEX
    Explanations

    elements related to suspenseful or thrilling narratives

    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
     lt
    -0.07
    одав
    -0.07
    鬼
    -0.07
     Hulk
    -0.06
    wij
    -0.06
     quot
    -0.06
    rique
    -0.06
    rage
    -0.06
     GOT
    -0.06
    IMS
    -0.06
    POSITIVE LOGITS
    estone
    0.06
     buck
    0.06
    arken
    0.06
     Patreon
    0.06
    entai
    0.06
     Follow
    0.06
    격
    0.06
    /cpp
    0.06
     Muse
    0.06
     kick
    0.06
    Activations Density 0.026%

    No Known Activations