© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71412
    Prev
    Next
    INDEX
    Explanations

    references to computer-generated imagery and special effects in film

    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
    оÑĢаз
    -0.08
    ENARIO
    -0.07
    avad
    -0.07
    åħĪçĶŁ
    -0.07
    esModule
    -0.07
     Burns
    -0.07
    agnost
    -0.07
    abyrinth
    -0.06
    ạt
    -0.06
    å¹ħ
    -0.06
    POSITIVE LOGITS
     technology
    0.08
     motion
    0.07
    technology
    0.07
     imm
    0.07
     computer
    0.07
     technological
    0.07
     tech
    0.07
     production
    0.07
     technologies
    0.07
     Techniques
    0.07
    Activations Density 0.014%

    No Known Activations