© 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. 5224
    Prev
    Next
    INDEX
    Explanations

    references to monsters and horror elements

    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
    éģĵè·¯
    -0.07
    serter
    -0.07
    usz
    -0.07
    obe
    -0.07
     плÑı
    -0.07
    SES
    -0.06
    yre
    -0.06
     Morm
    -0.06
     Evel
    -0.06
    obra
    -0.06
    POSITIVE LOGITS
    eti
    0.08
     motion
    0.07
     water
    0.06
    itom
    0.06
    umpt
    0.06
    gewater
    0.06
    owi
    0.06
    andard
    0.06
    motion
    0.06
     bi
    0.06
    Activations Density 0.000%

    No Known Activations