© 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. 15-LLAMASCOPE-RES-131K
    11. 88811
    Prev
    Next
    INDEX
    Explanations

    references to time-related updates and events

    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
    ameda
    -0.06
    ipples
    -0.06
     sym
    -0.06
     Period
    -0.06
     intens
    -0.05
    oog
    -0.05
    ida
    -0.05
    :
    -0.05
     sp
    -0.05
    oggles
    -0.05
    POSITIVE LOGITS
    .unbind
    0.09
    arb
    0.09
    arLayout
    0.08
    itere
    0.07
    _BIND
    0.07
    enton
    0.07
    ãĢĤæľ¬
    0.07
    TYPES
    0.07
    omit
    0.07
    bote
    0.07
    Activations Density 0.015%

    No Known Activations