© 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 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. 88635
    Prev
    Next
    INDEX
    Explanations

    references to specific groups or categories of people or entities

    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
     itself
    -0.10
    erece
    -0.07
     Blanc
    -0.07
    ve
    -0.07
    iversite
    -0.06
    971
    -0.06
    åįģåħ«
    -0.06
    à¸ķà¸Ļ
    -0.06
    /vector
    -0.06
    ernes
    -0.06
    POSITIVE LOGITS
     things
    0.09
     kinds
    0.08
    sek
    0.08
     words
    0.08
     guys
    0.07
     ones
    0.07
     days
    0.07
    ones
    0.07
    ãĤ¶ãĥ¼
    0.07
    quence
    0.07
    Activations Density 0.007%

    No Known Activations