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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 55857
    Prev
    Next
    INDEX
    Explanations

    references to horror movie tropes and gender roles

    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
    essel
    -0.07
    153
    -0.06
    LÄ°
    -0.06
     Yaz
    -0.06
     abs
    -0.06
     Magical
    -0.06
    aidu
    -0.06
     tail
    -0.06
    strup
    -0.06
    astreet
    -0.06
    POSITIVE LOGITS
     horror
    0.11
     Horror
    0.09
     gore
    0.07
     hockey
    0.07
    reur
    0.07
    hor
    0.07
     serial
    0.07
     Romero
    0.07
    ror
    0.07
    Fear
    0.07
    Activations Density 0.138%

    No Known Activations