© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75591
    Prev
    Next
    INDEX
    Explanations

    questions and affirmatives related to uncertainty 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
    kir
    -0.08
     klu
    -0.07
    edia
    -0.07
     Hutchinson
    -0.06
    ailles
    -0.06
    еÑģÑı
    -0.06
    ISTA
    -0.06
    acin
    -0.06
     blind
    -0.06
    aille
    -0.06
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.10
     then
    0.08
     thì
    0.08
     THEN
    0.07
     então
    0.07
     Then
    0.07
    abolic
    0.07
    975
    0.07
    Then
    0.07
    ãĥªãĥ¼
    0.06
    Activations Density 0.028%

    No Known Activations