© 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. 9-LLAMASCOPE-RES-131K
    11. 98685
    Prev
    Next
    INDEX
    Explanations

    actions and recommendations related to safety and proper usage

    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
    enheim
    -0.07
    ché
    -0.07
     emin
    -0.07
    inox
    -0.07
    eras
    -0.07
    esen
    -0.06
    uche
    -0.06
    adele
    -0.06
    iph
    -0.06
    emin
    -0.06
    POSITIVE LOGITS
     Platt
    0.06
     Kinh
    0.06
    ÏĦÏī
    0.06
     inn
    0.06
    cribe
    0.06
     Elli
    0.05
     Airways
    0.05
     scr
    0.05
     Scouts
    0.05
    otos
    0.05
    Activations Density 0.052%

    No Known Activations