© 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. 75929
    Prev
    Next
    INDEX
    Explanations

    references to film adaptations and the film industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    vanished
    -0.06
    км
    -0.06
     Roosevelt
    -0.06
    roke
    -0.06
    terra
    -0.06
    fers
    -0.06
    ft
    -0.06
    agh
    -0.06
    _mono
    -0.06
    wcs
    -0.06
    POSITIVE LOGITS
     movie
    0.10
     adaptations
    0.10
     film
    0.10
     adapt
    0.09
     adapted
    0.09
     adaptation
    0.09
    movie
    0.09
     movies
    0.09
    movies
    0.09
     Adapt
    0.08
    Activations Density 0.035%

    No Known Activations