© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 17050
    Prev
    Next
    INDEX
    Explanations

    mentions of paid leave and related policies

    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
    ettings
    -0.07
    ESİ
    -0.07
    /ion
    -0.07
    .Marshal
    -0.07
    ÅĻeh
    -0.07
    ein
    -0.07
    ophon
    -0.07
    /connect
    -0.07
    _nh
    -0.07
    ãĥĥãĤ«ãĥ¼
    -0.06
    POSITIVE LOGITS
    -for
    0.09
    /free
    0.08
    VERTISE
    0.07
    illac
    0.07
    /lic
    0.06
    ulumi
    0.06
    ãĤ¦ãĥ³
    0.06
    Content
    0.06
     content
    0.06
    -content
    0.06
    Activations Density 0.008%

    No Known Activations