© 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 EvalsExportsAPI 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. 88755
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting symbols

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

    Text that appears immediately before the end of a paragraph, often containing concluding remarks that wrap up the current thought before transitioning to a new paragraph or speaker.

    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
    ienne
    -0.07
    AMERA
    -0.07
    aje
    -0.07
    rani
    -0.07
    rrha
    -0.07
    uguay
    -0.07
    urette
    -0.07
    ActionCreators
    -0.07
    agma
    -0.07
    à¸ĩà¸ģ
    -0.07
    POSITIVE LOGITS
     Finally
    0.06
    ao
    0.06
     Lastly
    0.06
    ingo
    0.06
    è¹
    0.06
     Miscellaneous
    0.06
     v
    0.06
     last
    0.05
    Č↵
    0.05
    v
    0.05
    Activations Density 0.001%

    No Known Activations