© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87438
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize importance and necessity, particularly concerning recommendations and integral components in various contexts

    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
    ugg
    -0.06
    ÑĢей
    -0.06
    alm
    -0.06
    izon
    -0.06
     Salem
    -0.06
    озможно
    -0.06
    öl
    -0.06
    ican
    -0.06
    aa
    -0.06
    uala
    -0.05
    POSITIVE LOGITS
     vital
    0.13
     essential
    0.13
     importance
    0.12
     indispens
    0.12
     Importance
    0.12
    essential
    0.11
     required
    0.10
     Essential
    0.10
     necessary
    0.10
    éĩįè¦ģ
    0.10
    Activations Density 0.191%

    No Known Activations