© 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. 15-LLAMASCOPE-RES-131K
    11. 90499
    Prev
    Next
    INDEX
    Explanations

    references to lakes and related geographical 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
    lient
    -0.06
     resigned
    -0.06
     wet
    -0.06
     systematic
    -0.06
    juan
    -0.05
     Maritime
    -0.05
    errer
    -0.05
    å²Ĺ
    -0.05
    leigh
    -0.05
    ÑĢип
    -0.05
    POSITIVE LOGITS
    çķ
    0.08
     lake
    0.08
     Lake
    0.08
    Lake
    0.07
    lake
    0.07
    Å¡et
    0.07
    alnız
    0.07
     Tit
    0.07
    quin
    0.07
    ogi
    0.07
    Activations Density 0.038%

    No Known Activations