© 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. 4942
    Prev
    Next
    INDEX
    Explanations

    terms related to electronic and technological topics

    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
    ocoa
    -0.07
    isman
    -0.06
     Sad
    -0.06
    chef
    -0.05
     Stick
    -0.05
     Sw
    -0.05
    973
    -0.05
    ettel
    -0.05
     Fen
    -0.05
    quires
    -0.05
    POSITIVE LOGITS
    .cid
    0.07
    -dat
    0.07
    RSS
    0.07
     Ø´Ùĩ
    0.07
    ntag
    0.07
     actionTypes
    0.07
    èm
    0.07
    ombok
    0.07
    .predicate
    0.07
    oom
    0.07
    Activations Density 0.015%

    No Known Activations