© 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. 15-LLAMASCOPE-RES-131K
    11. 103942
    Prev
    Next
    INDEX
    Explanations

    references to media, particularly movies and comics

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

    Media recommendation content phrasing, particularly "Best" lists of entertainment content (movies, comics, anime) and recommendation phrases like "that you should reading" that appear in article titles and content directories.

    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
    htdocs
    -0.08
    ctic
    -0.06
    loor
    -0.06
     technical
    -0.06
    orex
    -0.06
    rozen
    -0.06
    dio
    -0.06
    ÑĢÑĥж
    -0.06
     bang
    -0.06
     Comic
    -0.06
    POSITIVE LOGITS
    cles
    0.07
    liste
    0.07
    list
    0.07
    anki
    0.07
    wald
    0.07
    shi
    0.07
    anel
    0.07
    lista
    0.06
    asset
    0.06
     immersion
    0.06
    Activations Density 0.028%

    No Known Activations