© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125887
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structures

    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
    utor
    -0.08
     patches
    -0.07
     strtok
    -0.07
    nox
    -0.07
     pads
    -0.07
    à¸ī
    -0.07
    िण
    -0.06
    ãĥ³ãĥģ
    -0.06
    straction
    -0.06
    imple
    -0.06
    POSITIVE LOGITS
    .parseInt
    0.07
     int
    0.07
    uzu
    0.07
    .GetInt
    0.06
    agram
    0.06
     parseInt
    0.06
    .hashCode
    0.06
    ÑĤÑĢа
    0.06
    64
    0.06
    oe
    0.06
    Activations Density 0.101%

    No Known Activations