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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61148
    Prev
    Next
    INDEX
    Explanations

    numerical and textual representations of telephone and event details

    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
    958
    -0.08
    959
    -0.08
    642
    -0.07
    811
    -0.07
    ffective
    -0.07
    966
    -0.07
    766
    -0.07
    464
    -0.07
    700
    -0.07
    611
    -0.07
    POSITIVE LOGITS
    isky
    0.07
    ediÄŁi
    0.07
    (SK
    0.07
     Coron
    0.07
     ziy
    0.06
     Lehr
    0.06
    interop
    0.06
    /tos
    0.06
    vel
    0.06
    γοÏį
    0.06
    Activations Density 0.011%

    No Known Activations