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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16278
    Prev
    Next
    INDEX
    Explanations

    information related to awards and recognition in literature and the arts

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

    Sentence-final statements that provide crucial information about relationships between subjects, often preceding conjunctions or transition phrases that introduce related information.

    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
     himself
    -0.09
    istrovstvÃŃ
    -0.07
    uthor
    -0.07
     his
    -0.07
    ugins
    -0.07
    Ðİ
    -0.07
    ples
    -0.06
    ä»ĸçļĦ
    -0.06
    itoris
    -0.06
    ications
    -0.06
    POSITIVE LOGITS
     both
    0.18
    两人
    0.16
    both
    0.16
     their
    0.16
    Their
    0.16
    äºĮ人
    0.16
     themselves
    0.16
     Their
    0.15
     Both
    0.15
     ambos
    0.15
    Activations Density 0.062%

    No Known Activations