© 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. 86618
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and definitions

    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
    uÅŁ
    -0.07
    _quota
    -0.07
    AXB
    -0.07
    ahy
    -0.07
    Ư
    -0.07
    rieve
    -0.07
    Ðĩ
    -0.07
     heightFor
    -0.07
    .trip
    -0.07
    lake
    -0.06
    POSITIVE LOGITS
    /high
    0.07
     urn
    0.06
    itz
    0.06
     McCorm
    0.06
    Ñīее
    0.06
    dong
    0.05
     Engl
    0.05
    åĪĬ
    0.05
     tum
    0.05
    pos
    0.05
    Activations Density 0.206%

    No Known Activations