© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 83987
    Prev
    Next
    INDEX
    Explanations

    occurrences of significant achievements or milestones

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

    End-of-paragraph punctuation marks (typically periods) followed by line breaks that signal the transition between different content sections or entries in compiled 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
    uju
    -0.06
    ÅĻich
    -0.06
    icide
    -0.06
    shima
    -0.06
    imi
    -0.06
    anus
    -0.06
    pyx
    -0.05
    yah
    -0.05
    Å¡k
    -0.05
    jah
    -0.05
    POSITIVE LOGITS
    stal
    0.08
    afc
    0.08
    اسÛĮ
    0.07
    jedn
    0.07
     ãĢ
    0.07
    ebek
    0.07
    _ASSUME
    0.07
    inne
    0.07
    _BS
    0.07
    esto
    0.07
    Activations Density 0.067%

    No Known Activations