© 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. 17-LLAMASCOPE-RES-131K
    11. 117870
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases indicating necessity or requirements

    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
    ego
    -0.06
     fas
    -0.06
    iot
    -0.06
    æĮĤ
    -0.06
    иÑģлов
    -0.06
    DDL
    -0.06
    ŀ
    -0.06
    cept
    -0.06
    dit
    -0.06
    alis
    -0.06
    POSITIVE LOGITS
     explicitly
    0.09
     explicit
    0.08
    æīįèĥ½
    0.08
    	explicit
    0.07
    explicit
    0.07
     special
    0.07
    936
    0.07
     specifically
    0.06
    ramework
    0.06
     manually
    0.06
    Activations Density 0.038%

    No Known Activations