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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3717
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to multiple entities in various contexts

    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
    142
    -0.07
     twice
    -0.06
     meter
    -0.06
    äl
    -0.06
     doubly
    -0.06
    131
    -0.06
     alone
    -0.06
    ÑĢаÑħ
    -0.06
     Twice
    -0.06
    anja
    -0.06
    POSITIVE LOGITS
    åIJĮæĻĤ
    0.10
     simultaneously
    0.10
    åIJĮæŶ
    0.10
     birden
    0.09
     simultaneous
    0.09
     simult
    0.08
    imeo
    0.08
    ï¼Įæ¯ı
    0.07
     each
    0.07
     DISCLAIM
    0.07
    Activations Density 0.054%

    No Known Activations