© 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. 15-LLAMASCOPE-RES-131K
    11. 27118
    Prev
    Next
    INDEX
    Explanations

    code constructs related to conditional statements and control flow

    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
    loff
    -0.07
     célib
    -0.06
    IOD
    -0.06
    adele
    -0.06
    εÏį
    -0.06
    é¢Ŀ
    -0.06
    룬
    -0.06
    acher
    -0.06
    spi
    -0.06
     tempt
    -0.06
    POSITIVE LOGITS
    469
    0.07
    rovers
    0.07
    liquid
    0.06
    :↵↵↵↵↵↵
    0.06
    elsen
    0.06
    ONUS
    0.06
     liquid
    0.06
    thenReturn
    0.06
     Liquid
    0.06
     Cunningham
    0.06
    Activations Density 0.032%

    No Known Activations