© 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. 78131
    Prev
    Next
    INDEX
    Explanations

    phrases related to permissions and app usage guidelines

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

    Double-slash symbols ("//") that mark single-line comments in various programming languages, often preceding explanatory text about code functionality.

    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
    ilia
    -0.07
    immel
    -0.06
    etes
    -0.06
     vel
    -0.06
     ech
    -0.06
    èµĦ
    -0.06
    osen
    -0.05
    ãĥģãĥ¥
    -0.05
     commonly
    -0.05
     sag
    -0.05
    POSITIVE LOGITS
     newer
    0.17
     recent
    0.15
     recently
    0.13
    recent
    0.13
     newest
    0.13
     older
    0.12
     Recent
    0.11
     Older
    0.11
     modern
    0.10
     lately
    0.10
    Activations Density 0.073%

    No Known Activations