© 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. 15-LLAMASCOPE-RES-131K
    6. 104248
    Prev
    Next
    INDEX
    Explanations

    uses of the conjunction "and."

    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
    овеÑĢ
    -0.06
    ight
    -0.06
    cco
    -0.06
     ast
    -0.06
    fte
    -0.06
     needless
    -0.06
    аÑģÑĤ
    -0.06
    ght
    -0.06
    éĶĭ
    -0.06
     then
    -0.06
    POSITIVE LOGITS
    andan
    0.07
    @brief
    0.07
    beiter
    0.07
    озÑı
    0.07
    .fd
    0.07
    ãĤ¿ãĥ«
    0.06
     SAC
    0.06
    кÑĢаÑĹ
    0.06
    .land
    0.06
    robat
    0.06
    Activations Density 0.013%

    No Known Activations