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. 4952
    Prev
    Next
    INDEX
    Explanations

    nested structures in code or programming syntax

    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
    è²»
    -0.06
    ache
    -0.06
    uta
    -0.06
    ÄįÃŃ
    -0.06
    805
    -0.05
     arms
    -0.05
    еÑģÑĮ
    -0.05
    ASM
    -0.05
    Unsafe
    -0.05
    ached
    -0.05
    POSITIVE LOGITS
    lesai
    0.07
    ANJI
    0.07
    .printStackTrace
    0.07
    Ľi
    0.06
    perc
    0.06
    lod
    0.06
    incare
    0.06
    olet
    0.06
    ĶåĽŀ
    0.06
    .gf
    0.06
    Activations Density 0.006%

    No Known Activations