© 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. 128481
    Prev
    Next
    INDEX
    Explanations

    phrases expressing degrees or qualities of enhancement and improvement

    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
    call
    -0.06
    иÑī
    -0.06
    stral
    -0.06
    sted
    -0.06
     call
    -0.06
    jin
    -0.06
     Mog
    -0.06
    arna
    -0.06
    YTE
    -0.06
    bucks
    -0.05
    POSITIVE LOGITS
    ergus
    0.08
     hol
    0.07
    APA
    0.07
    agrams
    0.07
    γÏĩ
    0.06
    apo
    0.06
     gridColumn
    0.06
    æŀľ
    0.06
     informed
    0.06
    497
    0.06
    Activations Density 0.020%

    No Known Activations