© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 83521
    Prev
    Next
    INDEX
    Explanations

    references to projects and scripts

    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
    /tiny
    -0.07
    ki
    -0.06
     Gon
    -0.06
    erb
    -0.06
    /groups
    -0.05
     APP
    -0.05
    hood
    -0.05
     mode
    -0.05
    unner
    -0.05
    olk
    -0.05
    POSITIVE LOGITS
    reuse
    0.08
    veloper
    0.08
    ULSE
    0.08
    lops
    0.07
    á»ijt
    0.07
    ets
    0.07
    ateral
    0.07
    uffman
    0.07
    éĢļãĤĬ
    0.07
    大åħ¨
    0.07
    Activations Density 0.051%

    No Known Activations