© 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. 83422
    Prev
    Next
    INDEX
    Explanations

    phrases that encourage searching for information or resources

    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
    iences
    -0.08
    illery
    -0.07
    vous
    -0.07
    -too
    -0.06
    icana
    -0.06
     proh
    -0.06
     mek
    -0.06
     franca
    -0.06
    ìĻķ
    -0.06
     soud
    -0.06
    POSITIVE LOGITS
    wal
    0.08
     details
    0.07
    ings
    0.07
     hiá»ĥu
    0.07
    .resources
    0.07
     Burl
    0.07
    vero
    0.07
    lay
    0.07
    ervo
    0.07
     out
    0.07
    Activations Density 0.009%

    No Known Activations