© 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. 2461
    Prev
    Next
    INDEX
    Explanations

    references to notable achievements or significant works

    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
     new
    -0.07
    rik
    -0.06
     newly
    -0.06
     Active
    -0.06
     recently
    -0.06
    èo
    -0.06
    andre
    -0.05
    zb
    -0.05
    ssa
    -0.05
     fixture
    -0.05
    POSITIVE LOGITS
    ogan
    0.07
    -care
    0.07
    ovu
    0.07
     career
    0.07
    OVE
    0.07
    ÄĻk
    0.07
    imson
    0.07
    career
    0.07
    Detach
    0.07
    siyon
    0.07
    Activations Density 0.016%

    No Known Activations