© 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. 75459
    Prev
    Next
    INDEX
    Explanations

    occurrences of locations and dates

    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
    buz
    -0.10
    ovna
    -0.09
    eba
    -0.09
    ÅĦst
    -0.08
    /WebAPI
    -0.07
    #ab
    -0.07
    buah
    -0.07
    оÑĢаÑı
    -0.07
    resa
    -0.07
    gregar
    -0.07
    POSITIVE LOGITS
     himself
    0.08
     “
    0.07
    åįļ士
    0.07
    âĢ¦
    0.06
    åħĪçĶŁ
    0.06
     Mr
    0.06
     kar
    0.06
     guy
    0.05
     protagonist
    0.05
     irrit
    0.05
    Activations Density 0.022%

    No Known Activations