© 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. 5136
    Prev
    Next
    INDEX
    Explanations

    ISBN numbers associated with books and publications

    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
    yor
    -0.08
    ugen
    -0.07
    ug
    -0.06
    ante
    -0.06
    ach
    -0.06
    enger
    -0.06
     Gilbert
    -0.06
    ht
    -0.06
    mere
    -0.05
     Claw
    -0.05
    POSITIVE LOGITS
    AGMA
    0.08
    istique
    0.08
    BuilderInterface
    0.07
    ÃŃž
    0.07
    kf
    0.07
    erator
    0.07
     Drag
    0.07
    ãģİ
    0.07
    ISTRY
    0.07
    itte
    0.07
    Activations Density 0.002%

    No Known Activations