© 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. 126850
    Prev
    Next
    INDEX
    Explanations

    phrases describing geographical locations and their features

    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
     Pell
    -0.06
    iais
    -0.06
    iaux
    -0.06
     tent
    -0.06
    hear
    -0.06
    antor
    -0.06
    çķ
    -0.05
    lad
    -0.05
    kud
    -0.05
    reau
    -0.05
    POSITIVE LOGITS
    tones
    0.08
    ÃĹ↵↵
    0.08
    å¦ĥ
    0.07
    è¡Ĺ
    0.07
    ache
    0.07
    [System
    0.07
    èŁ
    0.07
    ģ
    0.07
     STREET
    0.07
    ãĥ©ãĥ³ãĥī
    0.07
    Activations Density 0.041%

    No Known Activations