© 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. 55739
    Prev
    Next
    INDEX
    Explanations

    references to open access publishing and related concepts

    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
     snap
    -0.06
    otron
    -0.06
     React
    -0.06
    iki
    -0.06
    ahl
    -0.05
    ach
    -0.05
    -0.05
     wheel
    -0.05
    353
    -0.05
     Reynolds
    -0.05
    POSITIVE LOGITS
    KeyListener
    0.08
    viso
    0.08
    GRE
    0.08
    uetype
    0.07
    .GraphicsUnit
    0.07
    timeofday
    0.07
    :eq
    0.07
    åĬ¨çĶŁæĪIJ
    0.07
    azole
    0.07
    quo
    0.07
    Activations Density 0.001%

    No Known Activations