© 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. 59842
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing minimal requirements or conditions

    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
    istrovstvÃŃ
    -0.09
    ago
    -0.07
    ersiz
    -0.07
     addCriterion
    -0.07
    quite
    -0.07
     cÃłng
    -0.07
     öden
    -0.07
    reff
    -0.07
    ÅĻet
    -0.06
    å®ŀéĻħ
    -0.06
    POSITIVE LOGITS
     alespoÅĪ
    0.08
     partial
    0.07
    azer
    0.07
     least
    0.07
    esthetic
    0.06
     ÑħоÑĤÑı
    0.06
     atleast
    0.06
     certainly
    0.06
    azers
    0.06
     surely
    0.06
    Activations Density 0.015%

    No Known Activations