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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 104506
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate providing a service or content to the audience

    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
    æĺŃ
    -0.08
     Freund
    -0.07
    é¡ĺ
    -0.07
     konkrét
    -0.07
    orphic
    -0.07
    è£ķ
    -0.06
    anton
    -0.06
     Rowe
    -0.06
    -Identifier
    -0.06
    رÛĮÙĤ
    -0.06
    POSITIVE LOGITS
     news
    0.08
    inas
    0.07
     information
    0.07
     story
    0.07
     stories
    0.06
    iore
    0.06
     exclusive
    0.06
    iene
    0.06
    iar
    0.06
    886
    0.06
    Activations Density 0.005%

    No Known Activations