© 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. 5-LLAMASCOPE-RES-131K
    11. 125675
    Prev
    Next
    INDEX
    Explanations

    repeated references to specific time periods or instances

    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
    شتÙĩ
    -0.08
    ESIS
    -0.08
    Ñĥнк
    -0.07
    жд
    -0.07
     Pearce
    -0.07
     jadx
    -0.07
    steen
    -0.07
    ubat
    -0.07
     Newest
    -0.07
    arLayout
    -0.07
    POSITIVE LOGITS
    ylon
    0.07
    ycop
    0.06
    adu
    0.06
    ugo
    0.05
    219
    0.05
    irk
    0.05
     fart
    0.05
    0.05
    rawer
    0.05
    екÑĤоÑĢ
    0.05
    Activations Density 0.007%

    No Known Activations