© 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. 60003
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate continuation or repetition of subjects or actions

    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
    sel
    -0.08
    ãĥŃãĥ³
    -0.07
    uso
    -0.07
     ì¶ľìŀ¥
    -0.06
    amburg
    -0.06
    utom
    -0.06
    WER
    -0.06
    luv
    -0.06
    ìŀ¥ìĿ´
    -0.06
    artment
    -0.06
    POSITIVE LOGITS
     rest
    0.08
    butt
    0.06
     apart
    0.06
    éİ®
    0.06
    ax
    0.06
     remainder
    0.06
    reste
    0.05
     Kup
    0.05
     Boeh
    0.05
     details
    0.05
    Activations Density 0.009%

    No Known Activations