© 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. 121154
    Prev
    Next
    INDEX
    Explanations

    elements related to performance and achievement in creative projects

    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
    edom
    -0.07
    anden
    -0.07
    earch
    -0.07
    lint
    -0.07
    ivor
    -0.07
    rots
    -0.07
    amble
    -0.07
    ccb
    -0.06
    ancel
    -0.06
    çľ¾
    -0.06
    POSITIVE LOGITS
     contribution
    0.13
     role
    0.11
     contributions
    0.11
    contrib
    0.11
     contributed
    0.11
     Contribution
    0.10
    -role
    0.10
    role
    0.10
     ROLE
    0.10
     participation
    0.10
    Activations Density 0.073%

    No Known Activations