© 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. 1780
    Prev
    Next
    INDEX
    Explanations

    references to interactive storytelling or decisions in games

    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
     repr
    -0.07
    weeted
    -0.06
     channel
    -0.06
     Growth
    -0.06
     growth
    -0.06
     mot
    -0.06
     cent
    -0.06
     hatch
    -0.06
     sounding
    -0.06
    enberg
    -0.06
    POSITIVE LOGITS
     branching
    0.09
     Branch
    0.08
    thenReturn
    0.08
     OnTrigger
    0.07
     bran
    0.07
    Branch
    0.07
    ais
    0.07
     شاخÙĩ
    0.07
    tsx
    0.07
    ouse
    0.07
    Activations Density 0.044%

    No Known Activations