© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 29042
    Prev
    Next
    INDEX
    Explanations

    references to groups or categories of individuals or entities

    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
    ple
    -0.06
    (OP
    -0.06
     sociálnÃŃ
    -0.06
    æ§
    -0.06
    ÑĥлÑıÑĢ
    -0.06
    aque
    -0.06
     Guys
    -0.06
     Strikes
    -0.06
    iti
    -0.06
    zer
    -0.06
    POSITIVE LOGITS
     alike
    0.17
     similar
    0.11
     others
    0.10
     simil
    0.09
    others
    0.09
    similar
    0.08
    aille
    0.08
     comparable
    0.08
     similarly
    0.07
    odb
    0.07
    Activations Density 0.031%

    No Known Activations