© 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. 17-LLAMASCOPE-RES-131K
    11. 85747
    Prev
    Next
    INDEX
    Explanations

    references to significant actions or outcomes related to achievements and changes

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

    Function words and transition elements that establish causal relationships or qualify outcomes, especially those indicating how one thing enables or affects another.

    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
     turno
    -0.07
    vik
    -0.07
    âĦĸâĦĸ
    -0.07
    ture
    -0.07
     lucr
    -0.07
    unction
    -0.06
    ông
    -0.06
    pag
    -0.06
    надлеж
    -0.06
    .Builder
    -0.06
    POSITIVE LOGITS
     full
    0.07
     possibility
    0.07
     manufacture
    0.07
    405
    0.06
     possibilities
    0.06
     chances
    0.06
    ilan
    0.06
    ior
    0.06
     POSSIBILITY
    0.06
    collapse
    0.06
    Activations Density 0.114%

    No Known Activations