Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5224
    Prev
    Next
    INDEX
    Explanations

    patterns related to code snippets, particularly focusing on programming syntax and functions

    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
    incinn
    -0.07
    eton
    -0.07
    missive
    -0.07
    iÄįe
    -0.06
    oz
    -0.06
    iÄĩ
    -0.06
    xcf
    -0.06
    \Carbon
    -0.06
    }elseif
    -0.06
    ãĤ
    -0.06
    POSITIVE LOGITS
     see
    0.07
    https
    0.07
     consult
    0.07
     Rough
    0.07
     quoted
    0.07
     Wikipedia
    0.07
     quote
    0.07
    http
    0.07
    imas
    0.06
     read
    0.06
    Activations Density 0.020%

    No Known Activations