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

    Neuronpedia

    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. 56699
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inability or restrictions

    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
     intoler
    -0.06
    poss
    -0.05
    ↵
    -0.05
    yla
    -0.05
     Nash
    -0.05
     Meer
    -0.05
    -FIRST
    -0.05
    831
    -0.05
    reso
    -0.05
    lier
    -0.05
    POSITIVE LOGITS
    æŀľ
    0.08
    /locale
    0.08
     ApiService
    0.07
    Äįin
    0.07
    akin
    0.07
    ứ
    0.07
    upe
    0.07
    ÑĢоÑģÑĤо
    0.07
    εÏħ
    0.07
    finity
    0.07
    Activations Density 0.001%

    No Known Activations