© 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. 79168
    Prev
    Next
    INDEX
    Explanations

    assertions and claims about the state of public issues

    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
    enor
    -0.08
    ãģ£ãģ¨
    -0.06
    sole
    -0.06
    ansk
    -0.06
    oS
    -0.06
    -0.06
    agnostics
    -0.06
    inka
    -0.06
     expired
    -0.06
    нÑĮ
    -0.06
    POSITIVE LOGITS
    isel
    0.08
    hem
    0.08
    åĪ»
    0.07
    Locale
    0.07
    phin
    0.07
    δÏĮ
    0.07
    opath
    0.07
    μή
    0.07
    hait
    0.07
     اÙĦÙħÙħ
    0.06
    Activations Density 0.042%

    No Known Activations