© 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. 103922
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and data processing

    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
    abei
    -0.07
    hangi
    -0.07
    ekl
    -0.07
    «ĺ
    -0.07
    ahy
    -0.07
    reur
    -0.07
     Pod
    -0.07
    JI
    -0.06
     è¾
    -0.06
    .appspot
    -0.06
    POSITIVE LOGITS
    ÑĩÑĸ
    0.06
     Hust
    0.05
     Dra
    0.05
     Kramer
    0.05
     Guerrero
    0.05
     whole
    0.05
    vig
    0.05
    ÄĻ
    0.05
    itted
    0.05
    ↵
    0.05
    Activations Density 0.004%

    No Known Activations