© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 79260
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related structures within software or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Opening curly braces and code block beginnings in various programming languages, along with connecting words like "is", "has", and "are" that link clauses in technical documentation or research text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    _ALWAYS
    -0.07
    cken
    -0.07
    ACHINE
    -0.07
    ptoms
    -0.06
    alen
    -0.06
    ÏģοÏį
    -0.06
    astreet
    -0.06
    _minus
    -0.06
     +↵↵
    -0.06
    _NON
    -0.06
    POSITIVE LOGITS
     haven
    0.17
     Haven
    0.15
     belum
    0.15
    haven
    0.15
     hasn
    0.14
     chÆ°a
    0.14
     TBD
    0.13
     TODO
    0.12
     yet
    0.12
     unknown
    0.11
    Activations Density 0.171%

    No Known Activations