© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 69267
    Prev
    Next
    INDEX
    Explanations

    elements related to visual effects and their impact on film narratives

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Suff
    -0.06
    di
    -0.06
     lick
    -0.06
    ÑģÑĤаÑĤи
    -0.06
    amaz
    -0.06
    ta
    -0.06
    anio
    -0.06
    (strpos
    -0.05
    ZERO
    -0.05
     hood
    -0.05
    POSITIVE LOGITS
    Auth
    0.09
     detr
    0.08
     intr
    0.07
     impact
    0.07
    -auth
    0.07
    integral
    0.07
     Natural
    0.07
     interrupt
    0.07
     Authentic
    0.07
    adding
    0.07
    Activations Density 0.116%

    No Known Activations