© 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. 16343
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names and titles

    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
    #ac
    -0.10
    #ab
    -0.10
     srd
    -0.08
    ì£
    -0.08
    //{{
    -0.08
    ãĥŃãĥ³
    -0.08
    κά
    -0.08
    áme
    -0.07
    #af
    -0.07
    ütün
    -0.07
    POSITIVE LOGITS
    âĢ¦↵↵
    0.06
    âĢ¦↵
    0.06
    anmar
    0.06
    âĢ¦”
    0.05
    æ°ı
    0.05
     âĢ¦.
    0.05
    .AutoSizeMode
    0.05
     himself
    0.05
     commend
    0.05
     dys
    0.05
    Activations Density 0.008%

    No Known Activations