© 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. 61279
    Prev
    Next
    INDEX
    Explanations

    elements related to movie production and animation

    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
    bote
    -0.06
    avad
    -0.06
    ha
    -0.06
    éĸ
    -0.05
    ominator
    -0.05
     greed
    -0.05
    peon
    -0.05
    ia
    -0.05
    barcode
    -0.05
    ESP
    -0.05
    POSITIVE LOGITS
     Liberties
    0.08
    anken
    0.07
     matte
    0.07
    laps
    0.07
    -animation
    0.07
    ysa
    0.07
     shot
    0.07
     shoot
    0.07
    ispecies
    0.07
    enie
    0.07
    Activations Density 0.005%

    No Known Activations