© 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. 61118
    Prev
    Next
    INDEX
    Explanations

    references to official programs and their operations

    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
    isha
    -0.06
    apt
    -0.06
    buch
    -0.06
    abcdefghijklmnop
    -0.06
    ế
    -0.06
    arias
    -0.06
     PROGMEM
    -0.06
     ucfirst
    -0.06
    æı
    -0.06
    élé
    -0.06
    POSITIVE LOGITS
     temporarily
    0.09
     transfer
    0.08
     loan
    0.08
     permanent
    0.08
     temporary
    0.08
    ymb
    0.07
     TEMP
    0.07
     вÑĢем
    0.07
    transfer
    0.07
     tempor
    0.07
    Activations Density 0.021%

    No Known Activations