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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 93911
    Prev
    Next
    INDEX
    Explanations

    references to the video game "Shadow of Mordor" and its related elements

    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
    artment
    -0.07
    .Euler
    -0.07
    apia
    -0.07
    -describedby
    -0.07
    .UnitTesting
    -0.07
    atitude
    -0.06
    anto
    -0.06
    .synthetic
    -0.06
    åĬ
    -0.06
    /devices
    -0.06
    POSITIVE LOGITS
    ry
    0.09
    ed
    0.09
    less
    0.08
    ory
    0.08
    ing
    0.08
    ary
    0.07
    y
    0.07
    light
    0.07
     cast
    0.07
    yer
    0.06
    Activations Density 0.007%

    No Known Activations