© 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. 59230
    Prev
    Next
    INDEX
    Explanations

    phrases related to information dissemination and learning

    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
    adas
    -0.07
    ada
    -0.07
    imit
    -0.06
    loom
    -0.06
    Ê
    -0.06
    ScreenWidth
    -0.06
    _SUPPORT
    -0.05
     communities
    -0.05
    635
    -0.05
    Ŀ
    -0.05
    POSITIVE LOGITS
    reve
    0.11
    reveal
    0.10
     details
    0.10
     reveal
    0.10
     revealed
    0.10
     reveals
    0.10
     detail
    0.09
     revealing
    0.09
     revelation
    0.08
    -details
    0.08
    Activations Density 0.019%

    No Known Activations