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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14762
    Prev
    Next
    INDEX
    Explanations

    references to creation and resurrection themes

    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
    urum
    -0.08
    rement
    -0.07
    avl
    -0.07
    unami
    -0.07
    BorderColor
    -0.07
     lÃłnh
    -0.07
    subclass
    -0.07
    CTR
    -0.07
    à¹Īาย
    -0.07
    intval
    -0.07
    POSITIVE LOGITS
     anim
    0.07
     clay
    0.07
    anim
    0.07
     animate
    0.07
     Conway
    0.06
    -animate
    0.06
     animated
    0.06
    θÏģÏī
    0.06
     Animated
    0.06
     animation
    0.06
    Activations Density 0.007%

    No Known Activations