Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 29021
    Prev
    Next
    INDEX
    Explanations

    permissions related to audio and video capture in a software context

    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
    webpack
    -0.06
    ascus
    -0.06
    orney
    -0.06
    bury
    -0.06
    zy
    -0.06
    INU
    -0.06
    {}.
    -0.06
    ervers
    -0.06
    ripple
    -0.06
     Hudson
    -0.05
    POSITIVE LOGITS
    atform
    0.07
    [Index
    0.07
    [Test
    0.07
    ŀ
    0.06
    ystore
    0.06
    麦
    0.06
    edException
    0.06
    šov
    0.06
    upo
    0.06
    .bluetooth
    0.06
    Activations Density 0.002%

    No Known Activations