© 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. 87691
    Prev
    Next
    INDEX
    Explanations

    references to horror elements and supernatural creatures

    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
    ionage
    -0.07
    меÑĩ
    -0.06
    اÙĪ
    -0.06
     TextAlign
    -0.06
    jing
    -0.06
    å¦Ļ
    -0.06
    vana
    -0.06
    clair
    -0.06
    duce
    -0.06
    icros
    -0.06
    POSITIVE LOGITS
     entity
    0.07
     IEntity
    0.07
     Entity
    0.06
    /entity
    0.06
    istani
    0.06
     entities
    0.06
    oni
    0.06
    undi
    0.06
     feared
    0.06
    oksen
    0.06
    Activations Density 0.039%

    No Known Activations