© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 104176
    Prev
    Next
    INDEX
    Explanations

    elements related to horror and supernatural themes

    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
    endor
    -0.06
    .ImageAlign
    -0.06
     propos
    -0.06
     patch
    -0.05
    Ghost
    -0.05
    471
    -0.05
    547
    -0.05
     Patch
    -0.05
    esp
    -0.05
    ¼
    -0.05
    POSITIVE LOGITS
    heim
    0.08
    essler
    0.08
    kker
    0.07
    LLU
    0.07
    aldi
    0.07
     Controls
    0.07
    AGMA
    0.07
    agento
    0.07
    :].
    0.07
    iegel
    0.07
    Activations Density 0.019%

    No Known Activations