© 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 EvalsExportsAPI 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. 58647
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values and their formatting

    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
    èĻŁ
    -0.07
    ips
    -0.07
    uate
    -0.07
    åı·
    -0.06
    ippet
    -0.06
    isser
    -0.06
    aday
    -0.06
    imer
    -0.06
    olib
    -0.06
    ãģĻãģĻ
    -0.06
    POSITIVE LOGITS
     Pratt
    0.07
    avr
    0.07
     Cord
    0.07
    dub
    0.07
    GA
    0.07
    anja
    0.07
    ebi
    0.07
    -UA
    0.06
    ÑĤаж
    0.06
    dür
    0.06
    Activations Density 0.000%

    No Known Activations