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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28726
    Prev
    Next
    INDEX
    Explanations

    words related to commitment and dedication

    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
     verze
    -0.07
    fon
    -0.07
    or
    -0.07
    vez
    -0.06
    bild
    -0.06
    ÙĪد
    -0.06
    cid
    -0.06
    agle
    -0.06
    as
    -0.06
    awe
    -0.06
    POSITIVE LOGITS
     to
    0.08
    -urlencoded
    0.07
    .WinForms
    0.07
    HeaderCode
    0.07
    äºİ
    0.06
    apiro
    0.06
     situ
    0.06
    ë°ĺ
    0.06
     Equal
    0.06
    ãĤ·ãĥ¼
    0.06
    Activations Density 0.005%

    No Known Activations