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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 128264
    Prev
    Next
    INDEX
    Explanations

    references to literary or cinematic works and their genres

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

    The highlighted text appears to indicate titles of creative works (books, films, songs, episodes, etc.) that are often followed by genre descriptions, publication information, or brief summaries.

    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
     Comic
    -0.07
    سÛĮÙĨ
    -0.06
    åı¬
    -0.06
    izzly
    -0.06
    olem
    -0.06
    zew
    -0.06
     Quote
    -0.06
     rij
    -0.06
    ashtra
    -0.06
    etail
    -0.06
    POSITIVE LOGITS
     episode
    0.07
     song
    0.07
     release
    0.07
    song
    0.06
     film
    0.06
    ISODE
    0.06
    gregar
    0.06
     nov
    0.06
     book
    0.06
    ombres
    0.06
    Activations Density 0.486%

    No Known Activations