© 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. 9-LLAMASCOPE-RES-131K
    11. 96914
    Prev
    Next
    INDEX
    Explanations

    references to filmmaking and sound production

    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
    errat
    -0.07
     Reputation
    -0.07
     reputation
    -0.06
    ism
    -0.06
    rab
    -0.06
     industries
    -0.06
     Snake
    -0.06
    nerg
    -0.06
     Tutor
    -0.06
    est
    -0.06
    POSITIVE LOGITS
    اÙĩÛĮ
    0.08
    idy
    0.07
    .setViewport
    0.06
    quent
    0.06
    asure
    0.06
    pton
    0.06
    turnstile
    0.06
    rowable
    0.06
    IPC
    0.06
    .newInstance
    0.06
    Activations Density 0.000%

    No Known Activations